© 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. 19-RESID-POST-AA
    6. 69789
    Prev
    Next
    INDEX
    Explanations

    defining concepts

    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_19/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.19.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     induced
    -0.07
     Dude
    -0.07
     Towers
    -0.07
     worth
    -0.06
    跱
    -0.06
    .bus
    -0.06
    :@{
    -0.06
    An
    -0.06
     가운
    -0.06
    侨
    -0.06
    POSITIVE LOGITS
    sup
    0.07
    喹
    0.07
    ega
    0.06
    十九
    0.06
    ,result
    0.06
    ideshow
    0.06
    >*
    0.06
     الخبر
    0.06
    更好的
    0.06
    大叔
    0.06
    Activations Density 0.047%

    No Known Activations