© 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. 38766
    Prev
    Next
    INDEX
    Explanations

    numbers

    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
    1
    -0.53
    2
    -0.39
    8
    -0.38
    -0.38
    9
    -0.37
    7
    -0.37
    ï¼ij
    -0.33
    6
    -0.33
    ä¸ĥ个
    -0.30
    the
    -0.29
    POSITIVE LOGITS
    IBUT
    0.26
    ç½¢
    0.25
     fans
    0.25
     devastation
    0.24
     Cups
    0.24
    apia
    0.23
    Fans
    0.23
    athers
    0.23
     resin
    0.23
    emony
    0.22
    Activations Density 43.258%

    No Known Activations