© 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. 41134
    Prev
    Next
    INDEX
    Explanations

    executive

    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
     Themes
    -0.26
     conf
    -0.26
     her
    -0.25
     ens
    -0.25
    оÑĩ
    -0.24
     камеÑĢ
    -0.24
    缴æİ¥
    -0.24
     indirect
    -0.24
    æĦıæĢĿ
    -0.23
    oons
    -0.23
    POSITIVE LOGITS
    ä¸Ģé¢Ĺ
    0.30
    mailer
    0.28
    æľ¬æĬ¥è®°èĢħ
    0.28
    迤
    0.27
     Cow
    0.25
    oug
    0.24
    èħ¥
    0.24
    procedure
    0.24
    è¾ŀ
    0.24
     KEEP
    0.24
    Activations Density 1.883%

    No Known Activations