© 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. 43945
    Prev
    Next
    INDEX
    Explanations

    distance and scales

    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
    atric
    -0.08
    åįĥéĩij
    -0.08
    itsu
    -0.07
    æ±Łæ¹ĸ
    -0.07
    对åѦçĶŁçļĦ
    -0.07
    çĤŃ
    -0.07
     scoring
    -0.07
     predomin
    -0.06
    ilar
    -0.06
    æŃ£å¤§
    -0.06
    POSITIVE LOGITS
     distance
    0.09
     Distance
    0.09
     distances
    0.09
    è·ĿéĽ¢
    0.08
    è·Ŀ离
    0.08
    distance
    0.08
    Distance
    0.08
    åħīéĢŁ
    0.08
    çļĦè·Ŀ离
    0.08
    ר×Ĺ
    0.08
    Activations Density 0.002%

    No Known Activations