© 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. 23-TRANSCODER-HP
    7. 161882
    Prev
    Next
    INDEX
    Explanations

    code snippets

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_23.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.23.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     fourth
    -0.44
     four
    -0.43
     quart
    -0.42
     Fourth
    -0.41
     Four
    -0.40
    åĽĽä¸ª
    -0.39
    Fourth
    -0.39
    4
    -0.38
     quatre
    -0.38
    åĽĽ
    -0.36
    POSITIVE LOGITS
    ä¸īæĿ¡
    0.41
    ä¸īä½įä¸Ģä½ĵ
    0.40
    ä¸ī
    0.36
    ä¸īæĺ¯
    0.35
     three
    0.34
    ä¸ī项
    0.34
    ä¸īæľŁ
    0.33
    ä¸ī个
    0.32
    ä¸īç§į
    0.32
    è¿Ļä¸ī个
    0.31
    Activations Density 0.021%

    No Known Activations