© 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. 163406
    Prev
    Next
    INDEX
    Explanations

    code

    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
    å°Ĭ严
    -0.28
    еÑĢиал
    -0.26
     mois
    -0.26
    è®°èĢħ
    -0.26
    eurs
    -0.26
     journalist
    -0.26
    éĩįè¦ģåĨħ容
    -0.25
    æĦŁæŁĵèĢħ
    -0.25
    å¢ģ
    -0.24
    æĻ®éĢļè¯Ŀ
    -0.24
    POSITIVE LOGITS
    èĥĮä¸Ĭ
    0.28
     consultation
    0.28
     carefully
    0.28
    icken
    0.26
     consult
    0.26
     Pearce
    0.25
    ::__
    0.25
    究
    0.25
    æĿĸ
    0.25
     quitting
    0.24
    Activations Density 0.001%

    No Known Activations