© 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. 24416
    Prev
    Next
    INDEX
    Explanations

    research

    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
    æĬĬæĮģ
    -0.26
     Parties
    -0.26
    [`
    -0.25
    ä¼ģä¸ļåľ¨
    -0.24
    ä¸į代表
    -0.24
     lifestyles
    -0.23
    æĪļ
    -0.23
     Lorem
    -0.23
    趾
    -0.23
     `,↵
    -0.22
    POSITIVE LOGITS
    æķ°æį®åĪĨæŀIJ
    0.31
    ldata
    0.30
    éĢļè¿ĩ对
    0.29
    å¾Ĺä½ı
    0.26
    æĢĿãģĦåĩº
    0.26
    efa
    0.26
    æľĢåŁºæľ¬
    0.26
     princip
    0.26
    ndata
    0.25
     heavier
    0.24
    Activations Density 0.004%

    No Known Activations