© 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. 96164
    Prev
    Next
    INDEX
    Explanations

    Document titles/sections

    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
    è¿Ľåħ¥
    -0.28
    æ¿Ģåıij
    -0.26
    rules
    -0.26
    rule
    -0.26
     Prescott
    -0.25
    è¿Ľåħ¥äºĨ
    -0.24
    æĭľè®¿
    -0.24
    ä»Ħ
    -0.24
     rule
    -0.24
    ERE
    -0.23
    POSITIVE LOGITS
    çĽĤ
    0.27
    ativa
    0.26
     доÑĢ
    0.26
     tied
    0.25
    Handles
    0.25
    ãģļãģ«
    0.25
    è¾ķ
    0.24
    建åĨĽ
    0.24
    qual
    0.23
    amente
    0.23
    Activations Density 0.881%

    No Known Activations