© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Qwen2.5-7B-IT
    7. Resid Post - 131k
    9. 15-RESID-POST-AA
    11. 60741
    Prev
    Next
    INDEX
    Explanations

    the "Rapid Development Framework" header phrase found in CakePHP source file comment blocks.

    oai_token-act-pair · gpt-5-miniTriggered by @vetterc0
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-qwen2.5-7b-instruct/resid_post_layer_15/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    $fdata
    -0.07
    _shell
    -0.07
    .EVENT
    -0.07
    _disc
    -0.06
    -la
    -0.06
    的城市
    -0.06
    大夫
    -0.06
    \Client
    -0.06
    .ajax
    -0.06
     sued
    -0.06
    POSITIVE LOGITS
    模糊
    0.07
     BY
    0.07
     но
    0.07
    ATION
    0.07
    ____________
    0.07
    DOCTYPE
    0.07
     refin
    0.07
     olmadığını
    0.07
     specializing
    0.07
    第一届
    0.07
    Activations Density 0.138%

    No Known Activations