© 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. 15-RESID-POST-AA
    6. 15282
    Prev
    Next
    INDEX
    Explanations

    the

    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
    SPAN
    -0.07
     appréci
    -0.07
    =?
    -0.07
    ܘ
    -0.06
    ablo
    -0.06
    =!
    -0.06
    alogy
    -0.06
    オ
    -0.06
    ORM
    -0.06
    第一个
    -0.06
    POSITIVE LOGITS
    sgi
    0.07
    铅
    0.07
    自治区
    0.07
     cortical
    0.07
    ynet
    0.07
    .Inter
    0.07
    ,SLOT
    0.07
    쁨
    0.06
    渔
    0.06
    為
    0.06
    Activations Density 0.025%

    No Known Activations