© 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. 57389
    Prev
    Next
    INDEX
    Explanations

    The

    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
    /her
    -0.07
    и
    -0.07
    i
    -0.07
    ality
    -0.06
    éļĪ
    -0.06
    anco
    -0.06
    ات
    -0.06
    intl
    -0.06
    ortal
    -0.06
     (
    -0.06
    POSITIVE LOGITS
    jenigen
    0.12
    ly
    0.10
     halnya
    0.09
    ories
    0.09
    اÙĭ
    0.09
    ówczas
    0.08
    #@
    0.08
    æĤ¨åı¯èĥ½
    0.08
    缸è¾ħ缸æĪIJ
    0.08
    ewnÄħ
    0.08
    Activations Density 0.014%

    No Known Activations