© 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. 41010
    Prev
    Next
    INDEX
    Explanations

    Diverse topics

    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
     redes
    -0.30
    /ajax
    -0.27
     redhead
    -0.26
     franchises
    -0.25
    -publish
    -0.25
    éĢĬ
    -0.25
     Whip
    -0.24
     disap
    -0.24
    ä¸ĩäºĭ
    -0.24
     mixin
    -0.23
    POSITIVE LOGITS
    QR
    0.26
    éļĶ
    0.25
    dg
    0.25
     scheme
    0.25
    æ¸ĹéĢı
    0.24
     direct
    0.24
    By
    0.24
    åį±æľº
    0.24
    emer
    0.24
    iri
    0.24
    Activations Density 3.137%

    No Known Activations