© 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. 39334
    Prev
    Next
    INDEX
    Explanations

    condition, role, reason

    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
    uchia
    -0.07
    mö
    -0.07
    uÅŁt
    -0.07
    -vers
    -0.07
    erber
    -0.07
     nemlig
    -0.07
    Ñħина
    -0.06
     ìħĪ
    -0.06
    clus
    -0.06
    ogs
    -0.06
    POSITIVE LOGITS
    è²Ķ
    0.07
    rast
    0.07
    åĮºäººæ°ijæĶ¿åºľ
    0.06
    éĶ¢
    0.06
    ç¿°
    0.06
    зе
    0.06
    å²ĸ
    0.06
    çѱ
    0.06
    å¦Ĥèį¼
    0.06
    ÑĤÑģÑı
    0.06
    Activations Density 0.164%

    No Known Activations