© 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. 162576
    Prev
    Next
    INDEX
    Explanations

    perfectly

    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
    ãĢħ
    -0.30
    éĥ¢
    -0.28
    æĪIJ为ä¸ŃåĽ½
    -0.28
     respectfully
    -0.27
     Johannes
    -0.27
    æĢ»éĿ¢ç§¯
    -0.27
    keh
    -0.26
     constit
    -0.23
    èİ«
    -0.23
    aine
    -0.23
    POSITIVE LOGITS
    ucose
    0.31
    è
    0.28
    zure
    0.27
    ertia
    0.27
    etch
    0.27
    irst
    0.26
    alse
    0.26
    riot
    0.25
    htm
    0.24
    ESCO
    0.24
    Activations Density 0.001%

    No Known Activations