© 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. 40211
    Prev
    Next
    INDEX
    Explanations

    punctuation

    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
    ulous
    -0.30
    ·»
    -0.27
    -admin
    -0.26
    SENT
    -0.26
    airo
    -0.25
    /dist
    -0.25
     Fifth
    -0.25
    å®ŀè·µ
    -0.24
    éĽĨåĽ¢æĹĹä¸ĭ
    -0.24
    æĿ¥è®²
    -0.24
    POSITIVE LOGITS
    atee
    0.28
     none
    0.28
    对她
    0.27
    è·Łå¥¹
    0.27
    uden
    0.25
    bol
    0.25
    åĨįçĶŁèĥ½æºIJ
    0.25
     flap
    0.24
     lim
    0.24
    è·Łä»ĸ
    0.24
    Activations Density 0.228%

    No Known Activations