© 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. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 40172
    Prev
    Next
    INDEX
    Explanations

    variable name conflict

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    issen
    -0.08
    çĶŁäºİ
    -0.08
    napshot
    -0.07
    oundation
    -0.07
    igned
    -0.07
    psz
    -0.07
    è§ģè¿ĩçļĦ
    -0.07
    æµ·å°Ķ
    -0.07
    isman
    -0.07
     unseen
    -0.07
    POSITIVE LOGITS
    容æĺĵéĢłæĪIJ
    0.07
    .tm
    0.07
    ä¿
    0.07
    éģ¿è®©
    0.07
    ç¼
    0.07
    謹
    0.07
     conveniently
    0.07
     inadvertently
    0.07
     reuse
    0.07
    ç´Ľ
    0.06
    Activations Density 0.034%

    No Known Activations