© 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. 61599
    Prev
    Next
    INDEX
    Explanations

    weight ratio and smile

    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
    olé
    -0.09
    .clf
    -0.08
    atan
    -0.07
    auc
    -0.07
    lund
    -0.07
    airy
    -0.07
    ALE
    -0.07
    ole
    -0.07
    åīį款
    -0.07
    å¯ĵ
    -0.07
    POSITIVE LOGITS
    è¿ĩ大
    0.07
    ä¸Ģå®ļæľī
    0.06
    æľī太å¤ļ
    0.06
     C
    0.06
    otp
    0.06
    osis
    0.06
    ä»İä¸ļèµĦæł¼
    0.06
    Ø®ÙĦ
    0.06
    åı£æ°Ķ
    0.06
    被æ·ĺæ±°
    0.06
    Activations Density 0.003%

    No Known Activations