© 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. 163387
    Prev
    Next
    INDEX
    Explanations

    software licensing

    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
    çļĦä¼Łå¤§
    -0.28
     occ
    -0.26
    çļĦ好
    -0.25
    ismatic
    -0.25
    å½ĵä¸ĭ
    -0.25
     accomp
    -0.24
    è°Ģ
    -0.24
    çļĦç¾İ好
    -0.24
     bbw
    -0.23
    OCUS
    -0.23
    POSITIVE LOGITS
    æĢİ
    0.31
    åij¢
    0.27
     however
    0.26
     ayrı
    0.25
     therefore
    0.25
    stroy
    0.25
     nevertheless
    0.25
    .cz
    0.25
    shal
    0.24
    however
    0.24
    Activations Density 0.031%

    No Known Activations