© 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. 7619
    Prev
    Next
    INDEX
    Explanations

    inheritance from

    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
    деÑģÑıÑĤ
    -0.09
    -headed
    -0.09
    avanaugh
    -0.09
    HING
    -0.09
    icians
    -0.08
     lòng
    -0.08
    翼翼
    -0.08
    -eyed
    -0.08
     ervoor
    -0.08
     inset
    -0.08
    POSITIVE LOGITS
    æĢ§åľ°
    0.08
    ieves
    0.08
    eny
    0.08
     Fav
    0.08
     from
    0.07
    ä¸İåıijå±ķ
    0.07
    èĢħ们
    0.07
    財çĶ£
    0.07
    esk
    0.07
    ë°ĽìĿĢ
    0.07
    Activations Density 0.040%

    No Known Activations