© 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. 23247
    Prev
    Next
    INDEX
    Explanations

    territory

    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
     sink
    -0.28
    ”.
    -0.26
     Carnegie
    -0.25
    ”).
    -0.24
    ”.↵↵
    -0.24
    "/></
    -0.24
    æ·¡æ°´
    -0.24
    ofil
    -0.24
    ertext
    -0.23
    èĨĽ
    -0.23
    POSITIVE LOGITS
    pod
    0.27
    å¹´ä¸ŃåĽ½
    0.25
     gradu
    0.25
    grad
    0.25
    odd
    0.24
     pods
    0.24
    å¢ŀæĮģ
    0.24
    ustainability
    0.24
    Sweden
    0.24
    coh
    0.24
    Activations Density 0.045%

    No Known Activations