© 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. 41275
    Prev
    Next
    INDEX
    Explanations

    Technical documents/research papers

    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
    åĨ³
    -0.26
    private
    -0.26
    PDOException
    -0.25
    FindObject
    -0.25
     devil
    -0.25
    建åįİ
    -0.25
    ucha
    -0.24
    èĩªæĿ¥
    -0.24
    æ±
    -0.24
    éļĶçĥŃ
    -0.24
    POSITIVE LOGITS
    lem
    0.28
    æ¡Ī
    0.28
     Benjamin
    0.28
    ordinator
    0.27
    .rf
    0.26
    éĤ£æł·
    0.26
    _bm
    0.26
     Ven
    0.25
    ÑĤоÑĢ
    0.25
     mort
    0.25
    Activations Density 0.085%

    No Known Activations