© 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. 5815
    Prev
    Next
    INDEX
    Explanations

    scientific/technical/legal contexts

    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
    æĹłæīĢè°ĵ
    -0.28
     dict
    -0.27
     tit
    -0.26
     swe
    -0.26
    nas
    -0.25
     christmas
    -0.25
    keh
    -0.25
     Kidd
    -0.24
     Budd
    -0.24
     ordering
    -0.24
    POSITIVE LOGITS
    ần
    0.30
    é»ijæļĹ
    0.27
    powered
    0.27
    onis
    0.26
    quila
    0.26
     @}
    0.26
    ç£Ļ
    0.25
    ä¼Ĭæĸ¯åħ°
    0.25
    移åĪ°
    0.24
    åľ°æ¯¯
    0.24
    Activations Density 0.004%

    No Known Activations