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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 23-TRANSCODER-HP
    7. 23944
    Prev
    Next
    INDEX
    Explanations

    the

    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
    bra
    -0.29
    è¿
    -0.28
    æĺ¯ä¸įåı¯èĥ½
    -0.27
    æĢĢåŃķ
    -0.27
    èįŀ
    -0.26
     trusts
    -0.26
    èĢĨ
    -0.26
    åŃ£
    -0.25
    è¤ĩ
    -0.25
    бÑĥд
    -0.25
    POSITIVE LOGITS
     Cookbook
    0.29
     Reads
    0.27
    apped
    0.27
    locales
    0.27
     Formatter
    0.26
     classifier
    0.26
    converter
    0.25
    frau
    0.25
     encoder
    0.25
     Repeat
    0.25
    Activations Density 0.101%

    No Known Activations