© 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. 39977
    Prev
    Next
    INDEX
    Explanations

    Names or initials

    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
    æĢĿ
    -0.28
     ar
    -0.25
    èıģ
    -0.25
    帽
    -0.25
     bist
    -0.24
     jour
    -0.23
     finger
    -0.23
     Yên
    -0.23
    íķ©
    -0.23
    finger
    -0.23
    POSITIVE LOGITS
    TZ
    0.27
    éĻ¤
    0.26
    éĺ²ç©º
    0.24
    浪
    0.23
    едак
    0.23
     Conrad
    0.23
     ìľĦíķĺìŬ
    0.23
    -trigger
    0.23
    éĵ¢
    0.23
    åĩºçİ°
    0.23
    Activations Density 0.055%

    No Known Activations