© 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. 19-TRANSCODER-HP
    7. 5708
    Prev
    Next
    INDEX
    Explanations

    Punctuation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_19.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.19.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    -INFRINGEMENT
    -0.25
    ç»ĦæĪIJ
    -0.24
     <|
    -0.24
    éĤij
    -0.23
    uit
    -0.23
     characters
    -0.23
     Panic
    -0.23
     booth
    -0.23
    ington
    -0.23
     MainMenu
    -0.23
    POSITIVE LOGITS
    å°±æĦıåij³çĿĢ
    0.25
     middle
    0.25
    æĸ¥
    0.24
    رÙĬÙĥ
    0.24
    esses
    0.24
    ürü
    0.24
    åĪĥ
    0.23
    _fa
    0.23
    éļIJ
    0.23
    Prototype
    0.23
    Activations Density 0.053%

    No Known Activations