© 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. 33-TRANSCODER-HP
    7. 52865
    Prev
    Next
    INDEX
    Explanations

    places names

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_33.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.33.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Kind
    -0.31
     aw
    -0.30
     r
    -0.28
     st
    -0.28
    ó
    -0.27
    é£İ
    -0.27
    FO
    -0.27
    chal
    -0.27
    3
    -0.26
     em
    -0.26
    POSITIVE LOGITS
    unker
    0.31
    lish
    0.29
    æ»Ĥ
    0.28
    unal
    0.27
     sprung
    0.26
    deal
    0.26
    æī§æķĻ
    0.26
     seiz
    0.26
     berlin
    0.25
     Vibr
    0.25
    Activations Density 0.004%

    No Known Activations