© 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. 40082
    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
    antal
    -0.26
    atif
    -0.26
    ä¸ĢæľŁ
    -0.26
    é«Ģ
    -0.26
    voy
    -0.26
    ilded
    -0.25
    ä¸ĢåĽ¢
    -0.25
    ahi
    -0.25
    är
    -0.25
    ष
    -0.25
    POSITIVE LOGITS
     abbreviated
    0.27
     marching
    0.27
     coerc
    0.25
     der
    0.24
    éĻį
    0.24
    çķĻ
    0.24
    æ²»
    0.24
    ãĥĢ
    0.24
     frozen
    0.24
     tackling
    0.24
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.