© 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. 40492
    Prev
    Next
    INDEX
    Explanations

    religion

    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
    æ·±æ¸Ĭ
    -0.29
    æĢ§å¼º
    -0.28
    æĢ§çļĦ
    -0.27
    æĢ§
    -0.27
    DMI
    -0.25
    _graphics
    -0.25
    ç¥ŀåĻ¨
    -0.25
    itten
    -0.25
    å¾Ģä¸Ĭ
    -0.25
    iron
    -0.24
    POSITIVE LOGITS
    elic
    0.25
    æĪIJçĨŁ
    0.25
    æĻģ
    0.25
     Bloc
    0.24
    iko
    0.24
     appar
    0.24
    *dt
    0.24
    好象
    0.23
    建åĨĽ
    0.23
     announced
    0.23
    Activations Density 0.285%

    No Known Activations