© 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. 27865
    Prev
    Next
    INDEX
    Explanations

    group on $n$ points or size goes to infinity

    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
    æŀĹçĭ¬
    -0.08
    flix
    -0.08
     Menc
    -0.08
    ANGAN
    -0.08
     **âĢ¢
    -0.08
    åħĭåĬĽ
    -0.07
    åĪĺçķħ
    -0.07
    æ½
    -0.07
    ä½ĻåĬĽ
    -0.07
    _CONST
    -0.07
    POSITIVE LOGITS
    éļıçĿĢ
    0.15
    æ¸IJ
    0.14
    éĢIJæ¸IJ
    0.14
     asympt
    0.13
     gradually
    0.13
    ä½ĨéļıçĿĢ
    0.13
     increasingly
    0.13
     progressively
    0.13
    ä¼ļéĢIJæ¸IJ
    0.13
    æ¸IJæ¸IJ
    0.12
    Activations Density 0.084%

    No Known Activations