© 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. 39276
    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
    seau
    -0.31
    GPU
    -0.27
    anders
    -0.25
    elly
    -0.25
    pert
    -0.24
     plague
    -0.24
    neau
    -0.24
    çķĻä¸ĭæĿ¥
    -0.24
    æķĪåĬĽ
    -0.24
     redhead
    -0.24
    POSITIVE LOGITS
    isten
    0.34
    lining
    0.26
     Arbor
    0.25
     Clim
    0.25
    UNCH
    0.25
    æ¯ıä¸Ģ次
    0.25
     document
    0.24
     докÑĥменÑĤ
    0.24
    EVER
    0.24
    poster
    0.24
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.