© 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
    2. Qwen3-4B
    3. 23-TRANSCODER-HP
    4. 162403
    Prev
    Next
    INDEX
    Explanations

    original

    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
    èĹı
    -0.28
    eel
    -0.26
    æ¸ħåĩī
    -0.26
    alty
    -0.25
    æįĨç»ij
    -0.24
    .charCodeAt
    -0.24
     imp
    -0.24
    NEL
    -0.24
    Ĺı
    -0.24
     encouragement
    -0.24
    POSITIVE LOGITS
    éĻĮçĶŁ
    0.32
    éĻĮçĶŁäºº
    0.29
     ballots
    0.28
     commute
    0.28
    æµģ产
    0.28
    ç¿Ĵ
    0.27
    unch
    0.27
     prefixes
    0.25
    ύ
    0.25
    æĺİ天
    0.25
    Activations Density 0.001%

    No Known Activations