© 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. 33-TRANSCODER-HP
    7. 53059
    Prev
    Next
    INDEX
    Explanations

    essential

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_33.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.33.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    模åŀĭ
    -0.26
    imer
    -0.25
     conferred
    -0.25
    人群ä¸Ń
    -0.25
     concess
    -0.25
     waar
    -0.24
    uff
    -0.24
    ä¸įå¦Ĥ
    -0.24
    Made
    -0.24
    -of
    -0.24
    POSITIVE LOGITS
     both
    0.44
     Both
    0.35
    both
    0.34
    Both
    0.33
     BOTH
    0.32
     mostly
    0.32
     neither
    0.32
    æĹ¥è®¯
    0.29
     Neither
    0.28
    egade
    0.28
    Activations Density 0.038%

    No Known Activations