© 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. 5453
    Prev
    Next
    INDEX
    Explanations

    technical/legal language & 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
    ye
    -0.28
     деÑĢ
    -0.26
    ä¸ī项
    -0.26
    .getRuntime
    -0.26
    æ¡¥
    -0.26
    Bind
    -0.25
    ä¸Ģæīĭ
    -0.25
    åѦä½į
    -0.25
    åĪ«
    -0.24
    ä½Ļ
    -0.24
    POSITIVE LOGITS
    éļĪ
    0.27
    oref
    0.26
     MOCK
    0.26
    aku
    0.25
    人éĹ´
    0.25
    /arch
    0.25
    å¾µ
    0.24
    ç³ľ
    0.24
    ')</
    0.24
    erable
    0.24
    Activations Density 0.061%

    No Known Activations