© 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. 40729
    Prev
    Next
    INDEX
    Explanations

    Citations

    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
    ythe
    -0.25
     INCLUDED
    -0.25
    åĨ³å®ļäºĨ
    -0.24
    æĥħåĨµè¿Ľè¡Į
    -0.24
    å±ķ
    -0.24
     bre
    -0.24
    çļĦ人æĿ¥è¯´
    -0.24
     cert
    -0.24
    INET
    -0.23
    -minded
    -0.23
    POSITIVE LOGITS
    ctions
    0.28
    å¢Ļ
    0.28
    esp
    0.27
    igator
    0.27
    è·ĭ
    0.27
    sav
    0.26
    ESP
    0.24
    QP
    0.24
    .tap
    0.24
    леп
    0.24
    Activations Density 0.186%

    No Known Activations