© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 15111
    Prev
    Next
    INDEX
    Explanations

    following thing with

    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
     Fulton
    -0.08
    ë§IJ
    -0.08
    loys
    -0.08
    utri
    -0.08
    ÈĽele
    -0.08
    tria
    -0.08
    eid
    -0.08
    arp
    -0.08
    书ç½ij
    -0.08
    é¸¡æ¯Ľ
    -0.08
    POSITIVE LOGITS
    :
    0.08
    åīį款
    0.07
    ):
    0.07
    æľī以ä¸ĭ
    0.07
    æľīä¸ĭåĪĹ
    0.07
    $:
    0.07
    ikus
    0.07
    ä¸Ĭè¿°
    0.06
     ìķĦëŀĺìĻĢ
    0.06
    æľīå¦Ĥ
    0.06
    Activations Density 0.028%

    No Known Activations