© 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. 11991
    Prev
    Next
    INDEX
    Explanations

    viewed as

    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
     reportedly
    -0.09
    åı·ç§°
    -0.09
    umeric
    -0.08
    roku
    -0.08
    ofire
    -0.08
    föl
    -0.08
    Įĵ
    -0.08
    eration
    -0.08
    æį®è¯´
    -0.08
     allegedly
    -0.07
    POSITIVE LOGITS
     extending
    0.06
     extensions
    0.06
    çļĦåIJ§
    0.06
    广ä¹ī
    0.06
    ä¸Ģæĥ³
    0.06
    _compat
    0.06
    åħĥå¹´
    0.06
    åı¤äºº
    0.06
    ually
    0.06
    ãģ¨ãģĹ
    0.06
    Activations Density 0.024%

    No Known Activations