© 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. 23-TRANSCODER-HP
    7. 25136
    Prev
    Next
    INDEX
    Explanations

    fractions, ratios, or multiples

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_23.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.23.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     gegenüber
    -0.29
    澡
    -0.28
     tempted
    -0.27
    å±ķæľĽ
    -0.27
     dolayı
    -0.25
    èµĽåIJİ
    -0.25
    aurus
    -0.25
    æĿ¥æºIJäºİ
    -0.25
    Rename
    -0.24
    $rs
    -0.24
    POSITIVE LOGITS
    åIJĮçŃī
    0.36
     effort
    0.30
    æĽ´å¤ļçļĦ
    0.30
     strength
    0.30
    çļĦåĬªåĬĽ
    0.29
     strengths
    0.28
     amount
    0.27
     effectiveness
    0.27
     Intersection
    0.27
    strength
    0.27
    Activations Density 0.003%

    No Known Activations