© 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. 5251
    Prev
    Next
    INDEX
    Explanations

    Plant cultivars/scientific names

    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
    èĩ£
    -0.28
    -begin
    -0.27
    eci
    -0.27
    thur
    -0.26
    (Py
    -0.26
     Scor
    -0.25
    -</
    -0.25
    社
    -0.25
    lems
    -0.25
    ãĤ¢ãĥ³
    -0.24
    POSITIVE LOGITS
    actus
    0.31
    oger
    0.30
    为ä¸Ńå¿ĥ
    0.29
    åĬ¨
    0.25
    .xticks
    0.24
    à¹Ħà¸Ĺ
    0.24
     excuse
    0.24
     despite
    0.24
    åħ¬
    0.24
     complement
    0.24
    Activations Density 0.016%

    No Known Activations