© 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. 41786
    Prev
    Next
    INDEX
    Explanations

    shown in Fig

    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
    обе
    -0.07
    å¤ļ次
    -0.06
    ÑijÑĢ
    -0.06
    å¿ĥæĢ§
    -0.06
    å¤ļ
    -0.06
    ondre
    -0.06
     Kamar
    -0.06
     erm
    -0.06
    aura
    -0.06
    @s
    -0.06
    POSITIVE LOGITS
    ç§ij夫
    0.08
    harma
    0.08
    egur
    0.08
    asco
    0.07
     Fig
    0.07
    è¿ŀåŁİ
    0.07
    Fig
    0.07
    å¦ĤåĽ¾
    0.07
    åı¯æĥ³
    0.07
    gers
    0.07
    Activations Density 0.084%

    No Known Activations