© 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. 26074
    Prev
    Next
    INDEX
    Explanations

    invention relates

    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
    éĺ³åİ¿
    -0.07
    åįģäºĮå¹´
    -0.06
    å®´å¸Ń
    -0.06
     Vend
    -0.06
    ç¦ıç¦Ħ
    -0.06
    æµĴ
    -0.06
    vy
    -0.06
    _SAMPL
    -0.06
    ç¾²
    -0.06
    DOI
    -0.06
    POSITIVE LOGITS
    æķĪ
    0.08
                                                ↵
    0.07
    cps
    0.07
    å®ļåIJij
    0.07
    æĶ¯
    0.07
    prites
    0.07
    igsaw
    0.07
    请éĢīæĭ©
    0.07
    èĢIJåĬ³
    0.07
    èģĶ
    0.07
    Activations Density 0.012%

    No Known Activations