© 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. 130309
    Prev
    Next
    INDEX
    Explanations

    fan

    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
    æĶ¶åĪ°äºĨ
    -0.31
    æİ¥åıĹäºĨ
    -0.27
    ä½łè§īå¾Ĺ
    -0.27
    Disclaimer
    -0.27
    ãģĤãĤĬãģĮãģ¨ãģĨãģĶãģĸãģĦãģ¾ãģĹãģŁ
    -0.26
     Clash
    -0.26
    urette
    -0.26
    åĩºçİ°äºĨ
    -0.25
     جاء
    -0.25
     came
    -0.25
    POSITIVE LOGITS
     usually
    0.88
     often
    0.75
     typically
    0.73
    éĢļ常
    0.71
    usually
    0.68
     Usually
    0.66
    éĢļ常æĺ¯
    0.65
    often
    0.61
     sometimes
    0.60
     Often
    0.60
    Activations Density 0.000%

    No Known Activations