© 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. 22-TRANSCODER-HP
    7. 130131
    Prev
    Next
    INDEX
    Explanations

    dates

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_22.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.22.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    alis
    -0.32
    注æĺİæĿ¥æºIJ
    -0.31
    edio
    -0.27
    æİ¥åľ°æ°Ķ
    -0.27
    lap
    -0.27
    èī¯æĢ§
    -0.27
    ä¸įèĩ³äºİ
    -0.27
    -vis
    -0.27
    AccessException
    -0.27
    好ä¸į好
    -0.27
    POSITIVE LOGITS
    cter
    0.28
     until
    0.28
    reate
    0.27
     gon
    0.27
    举
    0.26
     DRIVER
    0.25
     Tim
    0.25
    åŃĿ
    0.25
     зÑĥб
    0.24
    æĻļ
    0.24
    Activations Density 0.008%

    No Known Activations