© 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. 45182
    Prev
    Next
    INDEX
    Explanations

    point mutation or substitution

    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
    åIJĮæµİ
    -0.07
    åĩīäºĨ
    -0.07
     selves
    -0.07
    éĿ³
    -0.07
    abay
    -0.07
    丰缼
    -0.07
     raided
    -0.07
    ä¸įåºĶæ±Ĥ
    -0.07
     refreshed
    -0.07
    ç»Ń
    -0.07
    POSITIVE LOGITS
     alteration
    0.11
    æĶ¹åıĺ
    0.10
    æĶ¹åıĺäºĨ
    0.10
     affecting
    0.10
     altering
    0.10
     structural
    0.09
     alteração
    0.09
     Alter
    0.09
     alterations
    0.09
    /change
    0.09
    Activations Density 0.072%

    No Known Activations