© 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. 5819
    Prev
    Next
    INDEX
    Explanations

    mathematical/scientific formulas

    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
     Spit
    -0.26
    ï¼ģ');↵
    -0.25
     executing
    -0.25
    éĻIJãĤĬ
    -0.25
    该æ¡Ī
    -0.25
    没åķ¥
    -0.24
    ä»ĸæĽ¾
    -0.24
     executions
    -0.24
    roof
    -0.24
    å¤Ħå¢ĥ
    -0.24
    POSITIVE LOGITS
    akes
    0.28
     Dah
    0.27
    uch
    0.27
    arlo
    0.27
     Dover
    0.26
    è¹²
    0.25
     Ferry
    0.25
     dah
    0.25
     primary
    0.25
    aks
    0.24
    Activations Density 0.035%

    No Known Activations