© 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. 5271
    Prev
    Next
    INDEX
    Explanations

    Technical topics

    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
     corner
    -0.27
    éĤ£æ¬¡
    -0.26
    ieber
    -0.25
    åij¼
    -0.25
    à¸ģระà¸Ĺ
    -0.25
    .erb
    -0.24
     Orc
    -0.23
    "|
    -0.23
    __/
    -0.23
     coarse
    -0.23
    POSITIVE LOGITS
    ä¼ĺ
    0.30
     manifest
    0.26
     pattern
    0.26
    èĩªå·±åĸľæ¬¢
    0.25
     Pattern
    0.24
    (pattern
    0.24
    å·¥
    0.24
    éĢĤçĶ¨äºİ
    0.24
    sockets
    0.23
    è¾Ĥ
    0.23
    Activations Density 0.878%

    No Known Activations