© 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. 150309
    Prev
    Next
    INDEX
    Explanations

    continue

    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
    å±ŀäºİ
    -0.31
     em
    -0.29
    ä¸įå±ŀäºİ
    -0.28
    è½µ
    -0.28
    dpi
    -0.28
    ç»Ŀ对
    -0.28
    åħ³èģĶ
    -0.27
    åıª
    -0.26
    íĺ¸
    -0.26
     Kore
    -0.25
    POSITIVE LOGITS
     EVEN
    0.35
     even
    0.34
    even
    0.34
    _even
    0.32
     даже
    0.29
    -even
    0.29
     until
    0.29
     пÑĢодолжа
    0.28
     Even
    0.28
    Even
    0.28
    Activations Density 0.122%

    No Known Activations