© 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. 30376
    Prev
    Next
    INDEX
    Explanations

    astatic lesions

    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
    çĴ
    -0.07
    imina
    -0.06
    çĽ¸å¯¹çļĦ
    -0.06
    ¶
    -0.06
    æĹ
    -0.06
     respiro
    -0.06
    rophe
    -0.06
    à¹Ģà¸Ķà¹ĩà¸Ķ
    -0.06
    æľīèī²
    -0.06
    Winner
    -0.06
    POSITIVE LOGITS
    arate
    0.08
    èĪįå¾Ĺ
    0.07
    ysÅĤ
    0.07
    éĻħ
    0.07
    ocs
    0.07
    äf
    0.07
    è´°
    0.07
     promis
    0.07
    çĪ±ç¾İ
    0.07
    áf
    0.07
    Activations Density 0.002%

    No Known Activations