© 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. 47410
    Prev
    Next
    INDEX
    Explanations

    structure or form

    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
    stable
    -0.08
    ablement
    -0.08
    acco
    -0.07
     vặt
    -0.07
    åĪ°æĤ¨çļĦ
    -0.07
    بار
    -0.06
    åħ¬å®īéĥ¨éŨ
    -0.06
    inos
    -0.06
    stel
    -0.06
     ÙħدÙī
    -0.06
    POSITIVE LOGITS
    /format
    0.10
    ç»ĵæŀĦä¸İ
    0.10
    ç»ĵæŀĦåĴĮ
    0.09
    ç»ĵæŀĦ
    0.09
     structure
    0.08
    ç»ĵæŀĦä¸Ń
    0.08
     reminiscent
    0.08
    çĽ¸ä¼¼çļĦ
    0.08
    ç»ĵæŀĦçļĦ
    0.08
    å¾Īåĥı
    0.08
    Activations Density 0.056%

    No Known Activations