© 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. 29424
    Prev
    Next
    INDEX
    Explanations

    map when

    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
    ÐĶÐĶ
    -0.08
    _FT
    -0.08
    åıĪå¤ļ
    -0.07
    askan
    -0.07
    ÐĵÐĺ
    -0.07
    ä¸įæĹ©
    -0.07
    ادا
    -0.07
    ipi
    -0.07
    eho
    -0.07
    èĻ
    -0.07
    POSITIVE LOGITS
     fam
    0.07
    oint
    0.06
    迹
    0.06
    ched
    0.06
    iff
    0.06
     embl
    0.06
    æ¢Ń
    0.06
    _compat
    0.06
    _che
    0.06
    ios
    0.06
    Activations Density 0.004%

    No Known Activations