© 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. 5292
    Prev
    Next
    INDEX
    Explanations

    technical content

    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
    èIJ½
    -0.28
    -vis
    -0.26
    imens
    -0.26
    åıĭåĸĦ
    -0.26
    igos
    -0.26
    illery
    -0.25
    ç»Ĩ
    -0.25
    Visit
    -0.25
     visiting
    -0.25
    _vis
    -0.25
    POSITIVE LOGITS
    æĪijä¸įçŁ¥éģĵ
    0.28
    =min
    0.26
    ä¹Łä¸įèĥ½
    0.25
    æĽ²
    0.24
    -index
    0.24
    Late
    0.24
     min
    0.23
    åģļèµ·
    0.23
     Late
    0.23
     æĽ
    0.23
    Activations Density 0.010%

    No Known Activations