© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 23-TRANSCODER-HP
    7. 161995
    Prev
    Next
    INDEX
    Explanations

    Code, games, and random text

    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
    ç½®
    -0.30
     protocols
    -0.26
    å°ijäºĨ
    -0.25
    åı»
    -0.25
    éĿĴæĺ¥
    -0.24
    urlencode
    -0.24
    ROME
    -0.23
    preh
    -0.23
    IOS
    -0.23
     prepaid
    -0.23
    POSITIVE LOGITS
    Authors
    0.28
    æ¸ħæĻ¨
    0.27
    åĤįæĻļ
    0.26
     tallest
    0.26
    éĢ
    0.25
    bers
    0.25
     scam
    0.25
    æ²
    0.25
     taller
    0.24
     Tonight
    0.24
    Activations Density 0.000%

    No Known Activations