© 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. 25-TRANSCODER-HP
    7. 106917
    Prev
    Next
    INDEX
    Explanations

    Reducing something

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_25.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.25.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    ooks
    -0.28
    éģĵ
    -0.27
    uity
    -0.27
    æ·±åıĹ
    -0.26
     Äijạo
    -0.26
    utch
    -0.25
    åģ¥åħ¨
    -0.25
    ç¦ģæŃ¢
    -0.25
    ór
    -0.25
     Reputation
    -0.24
    POSITIVE LOGITS
    .vaadin
    0.28
    IGO
    0.27
     carcin
    0.25
    TextLabel
    0.24
    oulos
    0.24
    REAM
    0.24
    felt
    0.23
    CANCEL
    0.23
    isposable
    0.23
     доп
    0.23
    Activations Density 0.939%

    No Known Activations