© 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. 24-TRANSCODER-HP
    7. 150761
    Prev
    Next
    INDEX
    Explanations

    random text snippets

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_24.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.24.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    st
    -0.28
    iol
    -0.27
    TABLE
    -0.27
    æł¸éħ¸
    -0.26
    票
    -0.26
    essions
    -0.26
     st
    -0.25
    å¼łå®¶
    -0.25
     pearl
    -0.25
     orientations
    -0.25
    POSITIVE LOGITS
    鸱
    0.31
    claimer
    0.29
    anim
    0.27
    马æĿ¥
    0.25
    .factory
    0.25
    itled
    0.24
    animated
    0.24
    æĿĢæīĭ
    0.24
    enko
    0.24
    editable
    0.24
    Activations Density 0.891%

    No Known Activations