© 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. 5346
    Prev
    Next
    INDEX
    Explanations

    Math and science formulas

    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
    anden
    -0.30
    æ¸ħåĩĢ
    -0.28
     Expl
    -0.27
    è·ĥ
    -0.27
    å¤ļæķ°
    -0.25
    phinx
    -0.25
    å¼ĢæľĹ
    -0.24
     popped
    -0.24
    ham
    -0.24
    _tac
    -0.24
    POSITIVE LOGITS
    immel
    0.27
     vet
    0.26
     either
    0.25
     mornings
    0.24
    .clip
    0.24
    isma
    0.23
     limiting
    0.23
    ytt
    0.23
     Go
    0.23
     Vinci
    0.23
    Activations Density 0.338%

    No Known Activations