© 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. 5928
    Prev
    Next
    INDEX
    Explanations

    Indonesia

    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
    ÙĨ
    -0.26
    similar
    -0.24
    lain
    -0.24
    standing
    -0.24
    osite
    -0.23
    .RGB
    -0.23
    壤
    -0.23
    èĻ¹
    -0.23
    åįİ缼
    -0.23
    Clipboard
    -0.22
    POSITIVE LOGITS
     Braz
    0.27
    cly
    0.25
    estre
    0.24
    SPATH
    0.24
    æĿ¥è®²
    0.23
    ya
    0.23
    antro
    0.22
    ç¡IJ
    0.22
     dint
    0.22
    {$
    0.22
    Activations Density 4.043%

    No Known Activations