© 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. 163138
    Prev
    Next
    INDEX
    Explanations

    Science and medicine

    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
    èĸ®
    -0.28
    ÅĪ
    -0.27
    ania
    -0.26
     Wand
    -0.25
     duel
    -0.25
    éķ¿æŶéĹ´
    -0.25
    æĪ¢
    -0.25
    elps
    -0.25
    åħ¨éĿ¢èIJ½å®ŀ
    -0.24
    erate
    -0.24
    POSITIVE LOGITS
     cons
    0.29
    äºī
    0.28
    otron
    0.27
    ochrome
    0.27
    callee
    0.27
     trial
    0.25
     contingency
    0.24
    ibrator
    0.24
     called
    0.24
    ursion
    0.24
    Activations Density 0.003%

    No Known Activations