© 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. 30841
    Prev
    Next
    INDEX
    Explanations

    disorder, onset, properties

    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
    __()
    -0.09
    rolled
    -0.08
    丽çļĦ
    -0.07
    gings
    -0.07
    oge
    -0.07
    agno
    -0.07
    inesi
    -0.07
    OrUpdate
    -0.07
    ordo
    -0.07
    stens
    -0.07
    POSITIVE LOGITS
    符åIJĪè¦ģæ±Ĥ
    0.08
     but
    0.07
    ä½Ĩè¿Ļç§į
    0.07
    ä¸Ĭè¿ĩ
    0.07
    ä½Ĩ
    0.06
    ä½Ĩä¸įæĺ¯
    0.06
     maio
    0.06
    åı¯æĥľ
    0.06
    æĬ±çĿĢ
    0.06
     ìłģíķ©
    0.06
    Activations Density 0.040%

    No Known Activations