© 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. 35-TRANSCODER-HP
    7. 40637
    Prev
    Next
    INDEX
    Explanations

    EL

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_35.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.35.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    aw
    -0.38
    æľīçļĦ
    -0.33
     surrendered
    -0.31
    oa
    -0.29
    BK
    -0.27
    avras
    -0.27
    RefPtr
    -0.27
    B
    -0.26
    AW
    -0.26
    åĨħçļĦ
    -0.25
    POSITIVE LOGITS
    hs
    0.29
    åģļ人
    0.25
    punk
    0.25
    кÑģ
    0.25
    yect
    0.25
    faction
    0.24
    ksen
    0.24
     Exceptions
    0.24
     Oxygen
    0.24
    desk
    0.23
    Activations Density 29.642%

    No Known Activations