© 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. 39718
    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
     enf
    -0.28
     comp
    -0.28
     minimal
    -0.28
    ICES
    -0.26
    dpi
    -0.25
    SEN
    -0.25
    审
    -0.25
     ener
    -0.25
    pipeline
    -0.24
     compat
    -0.24
    POSITIVE LOGITS
    obot
    0.28
     Jub
    0.27
    åĬ£
    0.26
    ä»Ģ
    0.25
    çŃīå½¢å¼ı
    0.25
    arguments
    0.24
     races
    0.24
     getArguments
    0.24
    éŀł
    0.24
    åĽłä¸ºå®ĥ
    0.24
    Activations Density 0.120%

    No Known Activations

    This feature has no known activations.