© 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. 33431
    Prev
    Next
    INDEX
    Explanations

    WITHOUT WARRANTIES OR CONDITIONS

    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
    baum
    -0.08
    wares
    -0.07
    æĤ¨åı¯èĥ½
    -0.07
    zeug
    -0.07
     Ritch
    -0.07
    кÑģÑĥ
    -0.07
    .dest
    -0.07
    罩
    -0.07
    丽
    -0.07
    ä¸Ńä¸ĵ
    -0.07
    POSITIVE LOGITS
    adh
    0.07
    clam
    0.07
    adó
    0.07
    è¯ģæį®è¯ģæĺİ
    0.06
    InView
    0.06
    ajor
    0.06
    ç²ĺåľŁ
    0.06
    druck
    0.06
    æ²¹çĽIJ
    0.06
    edBy
    0.06
    Activations Density 0.001%

    No Known Activations