© 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. 88422
    Prev
    Next
    INDEX
    Explanations

    Math problems

    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
    åĪĨå¸ĥåľ¨
    -0.27
    åĽłä¸ºå¥¹
    -0.27
    ä½Ĩ她
    -0.27
    éķ³
    -0.25
    ÑģÑĤÑĮ
    -0.25
    ftime
    -0.25
     innings
    -0.25
    æŶéĹ´ä¸º
    -0.25
    ä¸ĢåŃĹ
    -0.25
    tÃŃ
    -0.24
    POSITIVE LOGITS
    ä¼łè¨Ģ
    0.26
    åĪ«äººçļĦ
    0.26
    诸侯
    0.26
    ilent
    0.25
    注å®ļ
    0.25
    绸
    0.24
    磬
    0.23
     klein
    0.23
     Bend
    0.23
    coded
    0.23
    Activations Density 0.004%

    No Known Activations