© 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. 162602
    Prev
    Next
    INDEX
    Explanations

    Activities after work/long day

    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
    ä¼ijæģ¯
    -0.44
    å®īéĿĻ
    -0.34
    ä¸įåıĹ
    -0.33
    å®īå®ģ
    -0.32
    çĿ¡çľł
    -0.31
    ä¼ijéĹ²
    -0.30
    éĿĻ
    -0.29
     ngủ
    -0.29
    寧
    -0.29
     sleep
    -0.29
    POSITIVE LOGITS
     contr
    0.29
     loads
    0.29
    ustr
    0.26
    loads
    0.26
     Ã¶ÄŁ
    0.25
    bon
    0.25
    çIJ¯
    0.25
    ei
    0.24
    umn
    0.24
    anken
    0.24
    Activations Density 0.003%

    No Known Activations