© 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. 88338
    Prev
    Next
    INDEX
    Explanations

    gibberish/incoherent text

    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
    -toggler
    -0.28
    Vtbl
    -0.27
    ÑģÑĤÑĥп
    -0.25
     Invalidate
    -0.24
    å¼ĢåIJ¯
    -0.24
    ariant
    -0.24
    åıĺåİĭ
    -0.23
    æĥħ人
    -0.23
    å¹ķåIJİ
    -0.23
     Kling
    -0.23
    POSITIVE LOGITS
    æĭ¼éŁ³
    0.31
    ieee
    0.29
    abit
    0.28
    osaic
    0.27
    ä¸Ģå®ļä¼ļ
    0.27
    га
    0.27
    鸳
    0.26
     mf
    0.26
     caution
    0.26
    åıįå¼¹
    0.25
    Activations Density 0.004%

    No Known Activations