© 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. 51508
    Prev
    Next
    INDEX
    Explanations

    horário, cosine, antigens, men, region

    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
    åħ¶ä¹IJ
    -0.09
    å°ĭ
    -0.08
    atan
    -0.07
    impa
    -0.07
    _parsed
    -0.07
    éĢ¼
    -0.07
    å¸Ĥæĸ°
    -0.07
     pit
    -0.07
     Parl
    -0.07
    æľīäºĽäºĭæĥħ
    -0.07
    POSITIVE LOGITS
     irrelevant
    0.10
    æĹłåħ³
    0.09
     inutil
    0.08
     unnecessary
    0.07
    ä½ĨæľĢç»Ī
    0.07
    enor
    0.07
     inutile
    0.07
    nostic
    0.07
    æĪļ
    0.07
    çĦ¡éĹľ
    0.07
    Activations Density 0.068%

    No Known Activations