© 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. 5733
    Prev
    Next
    INDEX
    Explanations

    year

    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
     negatives
    -0.28
    comed
    -0.26
    artial
    -0.26
    æīĺ管
    -0.26
    pmat
    -0.25
    å®¢åľº
    -0.25
    åĻªéŁ³
    -0.25
    OLL
    -0.25
    ammad
    -0.24
    ç»ĦåĽ¢
    -0.24
    POSITIVE LOGITS
    éĤ£åıª
    0.27
    text
    0.27
    undi
    0.26
     sÃŃ
    0.26
    partner
    0.26
    æĶ¶
    0.25
    å½ĵæĹ¥
    0.25
    fast
    0.24
     мÑĥзÑĭк
    0.24
     sign
    0.24
    Activations Density 0.020%

    No Known Activations