© 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. 163375
    Prev
    Next
    INDEX
    Explanations

    biographies (or summaries)

    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
     expectancy
    -0.27
    æį¢åı¥è¯Ŀ说
    -0.26
    åı¯æĥ³èĢĮ
    -0.26
    -inline
    -0.26
    fore
    -0.25
    oogle
    -0.25
    _NS
    -0.24
    èĢĮè¿Ļ
    -0.24
    çļĦè§Ĵèī²
    -0.23
    FB
    -0.23
    POSITIVE LOGITS
    isode
    0.29
    èĿī
    0.28
    åıĸå¾Ĺ
    0.28
    ä¹ĥ
    0.27
     zes
    0.26
    æľīåĪ©äºİ
    0.26
     imprint
    0.26
    çļĦç»ıåİĨ
    0.26
     './../../
    0.25
     born
    0.25
    Activations Density 0.003%

    No Known Activations