© 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. 32-TRANSCODER-HP
    7. 43550
    Prev
    Next
    INDEX
    Explanations

    Forest

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_32.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.32.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    éģ£
    -0.29
    .foundation
    -0.28
     FOOT
    -0.27
     IPs
    -0.27
    :".
    -0.26
    oster
    -0.24
    责任
    -0.24
     Abed
    -0.23
    ä¸Ģæľ¬ä¹¦
    -0.23
    Fixture
    -0.23
    POSITIVE LOGITS
    .rawValue
    0.30
    æ±Łå±±
    0.29
    æģ¨
    0.27
     allot
    0.26
    éĻIJ
    0.25
    ç«Ļéķ¿
    0.24
    æĻ¯
    0.24
    OrNil
    0.24
    osome
    0.24
     unle
    0.24
    Activations Density 0.000%

    No Known Activations