© 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. 38057
    Prev
    Next
    INDEX
    Explanations

    geometric shapes or patterns

    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
    åIJİèĢħ
    -0.09
    ickle
    -0.07
    etheus
    -0.07
     unders
    -0.07
    è¿ĩæĹ©
    -0.07
    erts
    -0.07
    åī¯äº§åĵģ
    -0.07
    åīįèĢħ
    -0.07
    oya
    -0.06
     Fuller
    -0.06
    POSITIVE LOGITS
    ä»Ķç»Ĩè§Ĥå¯Ł
    0.10
    åĽ¾æ¡Ī
    0.09
     Pentagon
    0.08
    鬱
    0.08
    çĸ¼çĪ±
    0.08
    æĮīè¦ģæ±Ĥ
    0.08
    çľĭåĽ¾
    0.08
    åĽ¾ä¸Ń
    0.07
     patterns
    0.07
     caption
    0.07
    Activations Density 0.018%

    No Known Activations