© 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. 7444
    Prev
    Next
    INDEX
    Explanations

    angular resolution

    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
    à¸Ĭี
    -0.09
    ÐķÐĻ
    -0.08
    æľªå¿ħ
    -0.08
    çīĪæĿĥå½ĴåİŁä½ľèĢħ
    -0.08
    æľ¬é¢ĺåĪĨæŀIJ
    -0.08
    éĺħè¯»æľ¬æĸĩåīį
    -0.07
    upid
    -0.07
    ÐłÐĿ
    -0.07
    apter
    -0.07
    daq
    -0.07
    POSITIVE LOGITS
    æºIJäºİ
    0.06
    åı¤èĢģçļĦ
    0.06
    åĨħå¿ĥæ·±å¤Ħ
    0.06
    éŁ§å¸¦
    0.06
     intrinsic
    0.06
    æĪIJç«ĭçļĦ
    0.06
     molecular
    0.06
     neural
    0.06
    èµ·æºIJäºİ
    0.06
     countless
    0.06
    Activations Density 0.109%

    No Known Activations