© 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. 11860
    Prev
    Next
    INDEX
    Explanations

    variable or patch names

    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
    tures
    -0.07
    жаÑħ
    -0.07
    ECK
    -0.07
    ÙĬØ´
    -0.07
    gings
    -0.07
    locs
    -0.07
    èı²åĪ©
    -0.06
    缴è¨Ģ
    -0.06
    еÑģÑĤв
    -0.06
    hap
    -0.06
    POSITIVE LOGITS
    quat
    0.08
    aye
    0.08
    项
    0.07
    ainer
    0.07
    è®°äºĭ
    0.07
    éĺ¶
    0.07
    еÑĩи
    0.07
     Tér
    0.07
    éĥ¨ä»½
    0.07
    occa
    0.07
    Activations Density 0.004%

    No Known Activations