© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 23-TRANSCODER-HP
    7. 162423
    Prev
    Next
    INDEX
    Explanations

    Numerical identifiers in text snippets

    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
    åİħ
    -0.30
    PEndPoint
    -0.27
    æĹ¥æ¶Īæģ¯
    -0.25
     conven
    -0.24
     pee
    -0.24
    inance
    -0.24
     QtGui
    -0.24
    对ä¼ģä¸ļ
    -0.23
     wall
    -0.23
     capital
    -0.23
    POSITIVE LOGITS
    bos
    0.27
    .tie
    0.26
    ä¸ĢäºĮ
    0.25
    ÑĢаз
    0.24
     ÑĤекÑĥÑī
    0.24
    Recommended
    0.24
    soc
    0.23
    ием
    0.23
    ç¾¼
    0.23
    yı
    0.23
    Activations Density 0.005%

    No Known Activations