© 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. 40477
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    Not in Any Lists

    No Comments

    Negative Logits
    便æĺ¯
    -0.28
    å¾ģ
    -0.26
    ä¹ŁæŃ£æĺ¯
    -0.26
    åĬŀäºĭå¤Ħ
    -0.25
    .handler
    -0.24
     carr
    -0.23
    mani
    -0.23
    ä»Ļå¢ĥ
    -0.23
    éĻ¤åİ»
    -0.23
    laws
    -0.23
    POSITIVE LOGITS
     crowned
    0.25
     elevation
    0.24
    poke
    0.23
    ÄĿ
    0.23
    umes
    0.23
    USAGE
    0.23
     stabil
    0.23
    liers
    0.23
    umed
    0.23
    #w
    0.22
    Activations Density 37.195%

    No Known Activations

    This feature has no known activations.