© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 14723
    Prev
    Next
    INDEX
    Explanations

    asking for clarification

    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
    åīįè¿°
    -0.08
    æŀģ为
    -0.08
    ati
    -0.07
    æĦ¿
    -0.07
    åIJİåį³åı¯
    -0.07
    edor
    -0.07
    åIJİæĸ¹åı¯
    -0.07
    åį³ä¾¿å¦ĤæѤ
    -0.07
    zgl
    -0.07
    ÃŃg
    -0.07
    POSITIVE LOGITS
     pretty
    0.08
    Hmm
    0.08
    retty
    0.08
    ujur
    0.07
    åħĪéĶĭ模èĮĥ
    0.07
    è¿ĺæĮº
    0.07
     Hmm
    0.07
    èĩªå·±çļĦæĥ³æ³ķ
    0.07
    ķ
    0.07
    azy
    0.06
    Activations Density 0.025%

    No Known Activations