© 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. 39294
    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
    å®ıè§Ĥ
    -0.31
    remen
    -0.29
    空
    -0.29
    广
    -0.28
    sure
    -0.27
    means
    -0.27
    oret
    -0.25
    æīĵå¼Ģ
    -0.25
    SRC
    -0.24
     kè
    -0.24
    POSITIVE LOGITS
    websocket
    0.26
    datum
    0.24
    èĢĮ导èĩ´
    0.24
    ntax
    0.23
    å¨ĺ
    0.23
    _TA
    0.22
    åķĸ
    0.22
     заÑı
    0.22
    å¦Ħ
    0.22
    endant
    0.22
    Activations Density 1.703%

    No Known Activations

    This feature has no known activations.