© 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. 12-TRANSCODER-HP
    7. 22447
    Prev
    Next
    INDEX
    Explanations

    will

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_12.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.12.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    èĦij
    -0.29
     tu
    -0.28
     cerebral
    -0.27
     lo
    -0.27
    ernal
    -0.27
    à¹Ĥล
    -0.26
     di
    -0.26
    ìĦ¼
    -0.26
    (lo
    -0.26
    lo
    -0.26
    POSITIVE LOGITS
    æľįåĬ¡æ°´å¹³
    0.30
    ä¿¡ç®±
    0.28
     embarrass
    0.27
    umbnail
    0.25
    енÑĮ
    0.25
    trail
    0.25
    çķ¿
    0.25
    éĴª
    0.24
     gutter
    0.24
    pcf
    0.24
    Activations Density 0.007%

    No Known Activations