© 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. 24892
    Prev
    Next
    INDEX
    Explanations

    Important/necessary

    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
    èıĺ
    -0.27
    sit
    -0.26
    unami
    -0.25
    å¸ĮæľĽèĥ½å¤Ł
    -0.25
    éĹªåħī
    -0.25
    .cgi
    -0.25
     impacted
    -0.24
    éļIJ
    -0.24
    akra
    -0.24
    gia
    -0.24
    POSITIVE LOGITS
     flank
    0.27
    /ns
    0.26
     introdu
    0.24
     hiá»ĩp
    0.24
    ä»Ļ
    0.24
    æĢ»éĥ¨
    0.24
     Intro
    0.23
    ?↵↵
    0.23
     flips
    0.23
    ?"↵↵
    0.23
    Activations Density 0.002%

    No Known Activations