© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 62878
    Prev
    Next
    INDEX
    Explanations

    boolean/number sequences

    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
    osat
    -0.07
    åľĨ梦
    -0.07
    /pro
    -0.06
    åĿļ强çļĦ
    -0.06
    è¿Ľåħ¥åĪ°
    -0.06
    åħ¨éĿ¢åıijå±ķçļĦ
    -0.06
    ElementType
    -0.06
     HAG
    -0.06
    -sem
    -0.06
     Hv
    -0.06
    POSITIVE LOGITS
    мп
    0.08
    ä¸į大
    0.08
    çĻ¾åħ¬éĩĮ
    0.08
     hÆ°á»Łng
    0.07
    ipa
    0.07
    -toggler
    0.07
    请èģĶç³»æĪij们
    0.07
    ohlen
    0.07
    agher
    0.07
    inea
    0.07
    Activations Density 0.004%

    No Known Activations