© 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. 39484
    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
    ä¸Ģç«Ļ
    -0.30
    ookies
    -0.27
    pto
    -0.26
    为æĤ¨
    -0.26
    ceptor
    -0.26
    é£ŀè·ĥ
    -0.26
    说åĩºæĿ¥
    -0.26
    legate
    -0.26
    尾巴
    -0.25
    å²IJ
    -0.24
    POSITIVE LOGITS
    ÙĬتÙĩ
    0.26
     adel
    0.25
    .locals
    0.24
     successes
    0.24
    丹
    0.24
     sins
    0.24
     Salem
    0.24
     sleeper
    0.23
     fflush
    0.23
     sécur
    0.23
    Activations Density 2.059%

    No Known Activations

    This feature has no known activations.