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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 41606
    Prev
    Next
    INDEX
    Explanations

    abstracts

    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_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
     comprising
    -0.08
    从严治党
    -0.07
    paredStatement
    -0.07
     informational
    -0.07
    Immutable
    -0.07
     Informationen
    -0.07
    文旅
    -0.06
    翡翠
    -0.06
     jsonify
    -0.06
     масло
    -0.06
    POSITIVE LOGITS
    .normal
    0.08
     zug
    0.08
    elong
    0.07
    Destructor
    0.07
    exo
    0.07
     slow
    0.06
    tero
    0.06
    (scale
    0.06
    人们的
    0.06
    /Sh
    0.06
    Activations Density 0.010%

    No Known Activations