© 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. 29203
    Prev
    Next
    INDEX
    Explanations

    nocturnal or deciduous

    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
    gul
    -0.09
    anon
    -0.08
    izzer
    -0.08
    åľ¨å¿ħ
    -0.08
    ÏģÏĨ
    -0.07
    æ¯Ļ
    -0.07
    æĮºèº«
    -0.07
     untreated
    -0.07
    æīįä¸įä¼ļ
    -0.07
    -serving
    -0.07
    POSITIVE LOGITS
    èĢĮéĿŀ
    0.13
     rather
    0.13
    rather
    0.11
    å±ħå¤ļ
    0.10
    èĢĮä¸įæĺ¯
    0.09
    à¹Ģà¸Ľà¹ĩà¸Ļหลัà¸ģ
    0.08
     plutôt
    0.08
    å·¥ä½ľåĪ¶
    0.08
     Rather
    0.08
    except
    0.08
    Activations Density 0.603%

    No Known Activations