© 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. 162636
    Prev
    Next
    INDEX
    Explanations

    Entrepreneurship

    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
    çĿĢ
    -0.29
    车载
    -0.26
    cores
    -0.25
     gib
    -0.25
    ETS
    -0.25
    UserService
    -0.24
    åľ¨æĦı
    -0.24
    GPS
    -0.24
     Guinness
    -0.23
    è¿ĩé«ĺ
    -0.23
    POSITIVE LOGITS
     independence
    0.26
    getSource
    0.26
     thinking
    0.26
    è¾ĵ
    0.26
    æĭĵ
    0.25
    veau
    0.25
    è·ijåĪ°
    0.25
     independently
    0.25
    ku
    0.25
    æºIJ
    0.24
    Activations Density 0.006%

    No Known Activations