© 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. 6443
    Prev
    Next
    INDEX
    Explanations

    punctuation

    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
    åİĿ
    -0.27
    ä¸ĩåħĥ以ä¸Ĭ
    -0.25
    颤
    -0.25
    PURE
    -0.25
    è¡Ķæİ¥
    -0.24
     lend
    -0.24
     therefore
    -0.24
    ->__
    -0.23
     accordingly
    -0.23
     tester
    -0.23
    POSITIVE LOGITS
    otec
    0.27
    icc
    0.26
    è¡Ĺ
    0.25
     congest
    0.25
    isé
    0.24
    ÑĮÑİ
    0.24
    spa
    0.24
    rete
    0.23
    reste
    0.23
     setActive
    0.23
    Activations Density 0.054%

    No Known Activations