© 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. 5189
    Prev
    Next
    INDEX
    Explanations

    mathematical operations

    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
    æŀī
    -0.29
     arrangements
    -0.28
     antic
    -0.25
    ä¸įå¼Ģ
    -0.25
    tat
    -0.25
     contro
    -0.24
     neutr
    -0.24
    arra
    -0.23
     spit
    -0.23
    CCA
    -0.23
    POSITIVE LOGITS
    æ¯Ľ
    0.27
     Pediatrics
    0.26
    ä¹ĭå¤Ħ
    0.26
    ix
    0.24
    äºĭåĬ¡
    0.24
    çı
    0.24
     Äijá»īnh
    0.23
    ilyn
    0.23
    çĮľ
    0.23
     Pied
    0.23
    Activations Density 0.044%

    No Known Activations