© 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. 5965
    Prev
    Next
    INDEX
    Explanations

    complex analytical writing

    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
     aff
    -0.29
    æķı
    -0.27
    缼
    -0.26
    管å±Ģ
    -0.26
     Sens
    -0.25
    antan
    -0.25
    -admin
    -0.25
    è¡ĮåĬ¨
    -0.24
     OTA
    -0.24
    instein
    -0.24
    POSITIVE LOGITS
    itles
    0.27
    ä»ħä¾ĽåıĤèĢĥ
    0.26
    este
    0.25
    çĶµå½±
    0.24
    imum
    0.24
     Höhe
    0.24
    eos
    0.24
     legalize
    0.24
    æĥł
    0.24
     lique
    0.23
    Activations Density 0.028%

    No Known Activations