© 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. 40699
    Prev
    Next
    INDEX
    Explanations

    Code, configuration snippets

    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
    ä½Ļ家
    -0.27
    леÑĢ
    -0.25
    -pic
    -0.25
    æµ®åĬ¨
    -0.25
     Bender
    -0.24
    éĻ¤å¤ĸ
    -0.24
    иÑģк
    -0.23
     remover
    -0.23
    .Toggle
    -0.23
     BaseController
    -0.23
    POSITIVE LOGITS
    a
    0.40
    abb
    0.33
    tt
    0.31
    tti
    0.31
    unn
    0.31
    ا
    0.31
    arpa
    0.31
    AAAA
    0.31
    o
    0.30
    utta
    0.30
    Activations Density 0.835%

    No Known Activations