© 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. 14-TRANSCODER-HP
    7. 40826
    Prev
    Next
    INDEX
    Explanations

    cryosurgery, questions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_14.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.14.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    .findElement
    -0.29
     paralle
    -0.28
     dap
    -0.27
    pon
    -0.26
    ä¸ĭæ»ij
    -0.25
    ä¸Ģåī¯
    -0.25
     Anch
    -0.25
    ÃŃv
    -0.24
     derivation
    -0.24
     behalf
    -0.24
    POSITIVE LOGITS
    è¯Ģ
    0.30
    Ĺı
    0.30
    ucc
    0.27
     Tone
    0.27
    tone
    0.26
    lider
    0.26
     costing
    0.26
    çī¹æĿĥ
    0.25
     States
    0.25
    _lot
    0.25
    Activations Density 0.145%

    No Known Activations