© 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. 61049
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    🆆
    -0.08
     Mohammad
    -0.07
    ແ
    -0.07
    파트
    -0.06
    (rand
    -0.06
     sustainability
    -0.06
     autonomous
    -0.06
    -that
    -0.06
    ㌦
    -0.06
    onomous
    -0.06
    POSITIVE LOGITS
    effects
    0.07
    BACK
    0.06
     jakie
    0.06
    形成的
    0.06
    _TRIANGLE
    0.06
     couple
    0.06
    Expect
    0.06
    ᕙ
    0.06
     hopping
    0.06
    _REGISTRY
    0.06
    Activations Density 0.533%

    No Known Activations