© 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. 6392
    Prev
    Next
    INDEX
    Explanations

    cholesterol

    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
    临
    -0.28
    athing
    -0.27
    骼
    -0.26
    antar
    -0.25
    _Object
    -0.25
    à¸Ńà¸ĩ
    -0.24
     Logical
    -0.24
    angers
    -0.24
    LCD
    -0.24
    为æĤ¨æıIJä¾Ľ
    -0.24
    POSITIVE LOGITS
    inton
    0.30
    æĿ¥è®²
    0.26
    æĶ¶è´Ń
    0.25
    erule
    0.24
    åij½
    0.23
    final
    0.23
    責
    0.23
    èĢĮè¨Ģ
    0.23
    ä¸ĢæŶ
    0.23
    çŁ¾
    0.23
    Activations Density 0.239%

    No Known Activations