© 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. 65049
    Prev
    Next
    INDEX
    Explanations

    fragmenting clusters, each cluster

    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
     dunque
    -0.10
    áÄį
    -0.09
    è¯´ä½ł
    -0.08
     likewise
    -0.08
    atchet
    -0.08
    ãĥ¬ãĥ«
    -0.08
    对äºİè¿ĻäºĽ
    -0.08
    ilot
    -0.08
    ska
    -0.08
     foregoing
    -0.08
    POSITIVE LOGITS
     randomly
    0.06
    ç¼Ī
    0.06
     IT
    0.06
    çļĦä¸Ģç³»åĪĹ
    0.06
    åľ¨ç»Ļ
    0.05
     sogenannten
    0.05
     gegebenen
    0.05
     milli
    0.05
     specified
    0.05
    äºĨä¸Ģç³»åĪĹ
    0.05
    Activations Density 0.001%

    No Known Activations