© 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. 56369
    Prev
    Next
    INDEX
    Explanations

    temporary variables

    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
    ä»»ä½ķéĹ®é¢ĺ
    -0.08
    ä»»ä½ķäºĭæĥħ
    -0.08
    acker
    -0.08
     **ãĢIJ
    -0.08
    å¦ĤåĽł
    -0.08
    ÐĵУ
    -0.08
    licht
    -0.07
    æ¹ĥ
    -0.07
    kh
    -0.07
    ieux
    -0.07
    POSITIVE LOGITS
    æĹ
    0.07
    enste
    0.06
    0.06
    çĴIJ
    0.06
    ë§Īëĭ¤
    0.06
    UPS
    0.06
    LTE
    0.06
    æī«æııäºĮç»´çłģ
    0.06
    ä¸ĢåĪĻ
    0.06
    apsed
    0.06
    Activations Density 0.150%

    No Known Activations