© 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. 40239
    Prev
    Next
    INDEX
    Explanations

    awa

    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
    estring
    -0.28
    estar
    -0.28
    åŁİå¸Ĥ群
    -0.27
    éļĶå£ģ
    -0.25
    -than
    -0.25
    BEL
    -0.25
    thane
    -0.25
    ино
    -0.25
    åįĸç»Ļ
    -0.25
    ä¸įæķ¢
    -0.24
    POSITIVE LOGITS
    æĬ¹
    0.28
    马
    0.28
    UY
    0.28
    oment
    0.27
     spo
    0.26
    jab
    0.25
    éĤ±
    0.24
    æĺ¾
    0.23
    绵
    0.23
    nerRadius
    0.23
    Activations Density 0.219%

    No Known Activations