© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 22-TRANSCODER-HP
    7. 111236
    Prev
    Next
    INDEX
    Explanations

    room

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_22.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.22.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    xes
    -0.28
    thouse
    -0.28
    passes
    -0.27
    iri
    -0.26
     suicides
    -0.26
    logan
    -0.26
    swire
    -0.26
    ports
    -0.26
    ÑģÑĤан
    -0.25
    uly
    -0.25
    POSITIVE LOGITS
    åĪ°è´¦
    0.37
    ek
    0.32
    plan
    0.29
    æĺİç»Ĩ
    0.28
     plan
    0.27
    ä¼Łå¤§å¤įåħ´
    0.27
    anos
    0.25
     switch
    0.25
    æ¯į亲
    0.25
     planet
    0.25
    Activations Density 0.004%

    No Known Activations