© 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. 38716
    Prev
    Next
    INDEX
    Explanations

    Felipe/PE

    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
     toi
    -0.08
    _wo
    -0.07
    ند
    -0.07
     بالنسبة
    -0.07
    另一个
    -0.07
     swapping
    -0.07
    ball
    -0.07
    OrNil
    -0.07
    od
    -0.07
    Messaging
    -0.06
    POSITIVE LOGITS
     perspectives
    0.08
    槐
    0.08
    ฐ
    0.07
     française
    0.07
     flat
    0.07
     neurons
    0.07
    垂直
    0.07
     form
    0.07
     prism
    0.07
    鸲
    0.07
    Activations Density 0.003%

    No Known Activations