© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 19-TRANSCODER-HP
    7. 4868
    Prev
    Next
    INDEX
    Explanations

    code

    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
    ++↵↵
    -0.24
     hass
    -0.24
    athers
    -0.24
    uyá»ĩn
    -0.24
    Arthur
    -0.23
    åıĤ
    -0.23
    ennial
    -0.23
    åŁ¹åħ»
    -0.23
    æīĢåģļçļĦ
    -0.23
    Drug
    -0.22
    POSITIVE LOGITS
    CAM
    0.25
    ç»ıéªĮåĴĮ
    0.24
    lyph
    0.24
    ãģĦãģļãĤĮ
    0.24
    emble
    0.23
    _BOARD
    0.23
    prob
    0.23
    group
    0.23
    grams
    0.23
    memberof
    0.23
    Activations Density 0.004%

    No Known Activations