© 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. 7-RESID-POST-AA
    11. 10732
    Prev
    Next
    INDEX
    Explanations

    analogue

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-qwen2.5-7b-instruct/resid_post_layer_7/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     recurrent
    -0.07
    阶层
    -0.07
    !’
    -0.07
    敌人
    -0.07
     lobby
    -0.07
     punt
    -0.07
     최근
    -0.06
    geom
    -0.06
    행
    -0.06
     Advanced
    -0.06
    POSITIVE LOGITS
     /*<<<
    0.07
     noexcept
    0.07
     PropelException
    0.07
     -------------------------------------------------------------------------↵
    0.07
     Could
    0.07
    -Americans
    0.07
    )value
    0.06
    ᴥ
    0.06
     microscope
    0.06
    🙄
    0.06
    Activations Density 0.005%

    No Known Activations