© 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
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Qwen2.5-7B-IT
    4. Resid Post - 131k
    5. 23-RESID-POST-AA
    6. 775
    Prev
    Next
    INDEX
    Explanations

    say special characters

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-qwen2.5-7b-instruct/resid_post_layer_23/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.23.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Comics
    -0.07
    (env
    -0.07
    edu
    -0.07
    sembling
    -0.07
    |m
    -0.07
    plevel
    -0.06
     rescue
    -0.06
    .ctx
    -0.06
    考评
    -0.06
    inkle
    -0.06
    POSITIVE LOGITS
    _blob
    0.07
    啦
    0.07
    ANGED
    0.07
     giữ
    0.07
    海军
    0.07
    ガイ
    0.06
    ῾
    0.06
    roots
    0.06
     PATCH
    0.06
    屏障
    0.06
    Activations Density 0.006%

    No Known Activations