© 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. 39902
    Prev
    Next
    INDEX
    Explanations

    ified

    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
    SURE
    -0.26
    jd
    -0.22
    artment
    -0.22
    -eng
    -0.22
    çļĦé£İéĻ©
    -0.21
     virtual
    -0.20
    ossil
    -0.20
    utsch
    -0.20
     Covers
    -0.20
     shed
    -0.19
    POSITIVE LOGITS
    å·®å¼Ĥ
    0.26
    第ä¸ī个
    0.23
    bia
    0.23
    翻身
    0.22
    管çIJĨèĢħ
    0.22
    åīĬå¼±
    0.22
    åĦ¿
    0.22
    ä¸įæĥ³
    0.21
    åģıå·®
    0.21
    equalTo
    0.21
    Activations Density 35.427%

    No Known Activations