© 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. 48103
    Prev
    Next
    INDEX
    Explanations

    suffix -ish

    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
    ostos
    -0.08
    è¯Ŀ
    -0.07
    utig
    -0.07
    ya
    -0.07
     ngo
    -0.07
    ades
    -0.07
    è§Ĵ度
    -0.07
    à´¤àµģ
    -0.07
     versand
    -0.06
     tát
    -0.06
    POSITIVE LOGITS
    为è¾ħ
    0.11
    éĥ¨åĪĨç»ĦæĪIJ
    0.09
    çļĦéĥ¨åĪĨ
    0.08
    -ish
    0.08
    ä¸ĢäºĽçļĦ
    0.08
     некоÑĤоÑĢое
    0.08
    以åıĬä¸ĢäºĽ
    0.08
    ãĤĴ追åĬł
    0.08
    æĹ¥èµ·èĩ³
    0.08
    ToAdd
    0.07
    Activations Density 0.136%

    No Known Activations