© 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. 51255
    Prev
    Next
    INDEX
    Explanations

    test, times, errors

    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
    彫
    -0.08
    _aliases
    -0.08
    åŁł
    -0.08
    odb
    -0.07
    vend
    -0.07
    çķ¶åľ°
    -0.07
     herrer
    -0.07
    å½ĵåľ°
    -0.07
    è¹Ń
    -0.07
    влений
    -0.07
    POSITIVE LOGITS
    æѤæŶçļĦ
    0.08
    çŃ¹
    0.07
    ooks
    0.07
    è´Ŀ
    0.07
     total
    0.06
    onger
    0.06
    æѤæŶ
    0.06
    éĺ
    0.06
    éħįç½®çļĦ
    0.06
    è¯ķè¡Į
    0.06
    Activations Density 0.003%

    No Known Activations