© 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. 18964
    Prev
    Next
    INDEX
    Explanations

    preserve state

    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
    ded
    -0.08
    ä¼ĺèĥľ
    -0.08
    ÐĺÐij
    -0.07
    _years
    -0.07
    ä¹Ŀéĩį
    -0.07
     обнаÑĢÑĥжиÑĤÑĮ
    -0.07
    боÑĢо
    -0.07
    绾ç»İ
    -0.07
    edah
    -0.07
    nels
    -0.07
    POSITIVE LOGITS
    è®°å½ķä¸ĭ
    0.09
    è®°å½ķ
    0.08
    _backup
    0.08
     Preserve
    0.08
    ä¿ĿçķĻ
    0.08
    è®°ä¸ĭ
    0.08
    æĶ¶éĽĨæķ´çIJĨ
    0.08
     preservation
    0.08
     unaffected
    0.08
    è®°å½ķäºĨ
    0.07
    Activations Density 0.086%

    No Known Activations