© 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. 60711
    Prev
    Next
    INDEX
    Explanations

    Her Yoga Secrets

    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
    haj
    -0.08
    æ²³çķĶ
    -0.08
    ACTIVE
    -0.08
    egin
    -0.07
    hle
    -0.07
    秧
    -0.07
    ÄįÃŃ
    -0.07
    -END
    -0.07
    оле
    -0.07
    çIJĽ
    -0.07
    POSITIVE LOGITS
    ifr
    0.06
    åĩºçĶŁ
    0.06
    lyn
    0.06
    rought
    0.06
    ÑģÑĥлÑĮ
    0.06
    rou
    0.06
    åIJĦæ°ijæĹı
    0.06
    ou
    0.06
    urn
    0.06
    agno
    0.06
    Activations Density 0.618%

    No Known Activations