© 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. 162596
    Prev
    Next
    INDEX
    Explanations

    News articles

    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
    缼ä¸ĸ
    -0.26
    梨
    -0.26
    imonial
    -0.25
    ä½³
    -0.24
    ë¶Ī
    -0.24
    vendors
    -0.24
    åıĺæĢģ
    -0.24
    ä¸į满
    -0.23
    Invariant
    -0.23
    çļĦæĹ¶ä»£
    -0.23
    POSITIVE LOGITS
     windows
    0.26
    cka
    0.25
    İ·
    0.25
    yped
    0.25
    æĭ±
    0.24
    æĤ¬
    0.24
    elo
    0.24
    Windows
    0.24
    å¼ķ
    0.23
    èIJ¨
    0.23
    Activations Density 0.012%

    No Known Activations