© 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. 57054
    Prev
    Next
    INDEX
    Explanations

    range correlations

    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
    yks
    -0.07
    êle
    -0.07
    æ¼±
    -0.07
    prog
    -0.07
    åįĬæķ°
    -0.07
    å¦ŀ
    -0.07
    æ±ĩéĽĨäºĨ
    -0.07
    _runs
    -0.07
     liter
    -0.07
    æ¸ĵ
    -0.07
    POSITIVE LOGITS
    çļĦè·Ŀ离
    0.09
     mediated
    0.09
    -distance
    0.08
    çĤ¹å¯¹çĤ¹
    0.08
    (radius
    0.08
    æķ£å°Ħ
    0.08
    è¿ľè·Ŀ离
    0.08
     efet
    0.07
     radi
    0.07
    lim
    0.07
    Activations Density 0.006%

    No Known Activations