© 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. 40336
    Prev
    Next
    INDEX
    Explanations

    Mixed data and text snippets

    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
     *.
    -0.28
    velle
    -0.27
    Äįe
    -0.25
    ÙĤر
    -0.25
    宫
    -0.24
    æł·åŃIJ
    -0.24
    å®®
    -0.24
    odu
    -0.24
     Pen
    -0.23
    amps
    -0.23
    POSITIVE LOGITS
    èŃ
    0.28
    ardin
    0.25
     Rubio
    0.25
    å¿ĺ
    0.25
    /repository
    0.25
    ronym
    0.24
     swell
    0.24
    åĮ¿åIJį
    0.23
    libft
    0.23
     peas
    0.23
    Activations Density 0.195%

    No Known Activations