© 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. 30-TRANSCODER-HP
    7. 95606
    Prev
    Next
    INDEX
    Explanations

    legal proceedings

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_30.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.30.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    aida
    -0.28
    imized
    -0.27
     Action
    -0.26
    .ActionListener
    -0.25
    æ°IJ
    -0.25
    åĨį说
    -0.25
    обÑĢа
    -0.25
    .plus
    -0.24
    _DECLARE
    -0.24
    oved
    -0.24
    POSITIVE LOGITS
     stay
    0.34
     adj
    0.31
     commute
    0.29
     stayed
    0.29
     stays
    0.29
    engers
    0.28
    urger
    0.27
    stay
    0.27
     Stay
    0.27
     discharge
    0.27
    Activations Density 1.041%

    No Known Activations