© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 35-TRANSCODER-HP
    7. 39550
    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
    noon
    -0.33
    unner
    -0.30
    ijo
    -0.30
    announce
    -0.28
    IBUTE
    -0.28
    åIJĪåĩ»
    -0.28
     Riding
    -0.28
    æµ´
    -0.28
    Infrastructure
    -0.28
    篱
    -0.28
    POSITIVE LOGITS
     in
    0.46
     aut
    0.43
     can
    0.43
    ,
    0.42
     s
    0.42
     is
    0.42
     post
    0.41
     p
    0.41
     def
    0.40
     cal
    0.40
    Activations Density 0.003%

    No Known Activations

    This feature has no known activations.