© 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. 19471
    Prev
    Next
    INDEX
    Explanations

    lists characteristics history columns

    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
    ont
    -0.06
    æľºåħ³
    -0.06
     Pres
    -0.06
     Gam
    -0.06
     C
    -0.06
    å®ħ
    -0.06
    '
    -0.06
    æľªè¢«
    -0.06
    üe
    -0.06
    nt
    -0.05
    POSITIVE LOGITS
    uken
    0.10
    åIJĦæľīåIJĦ
    0.08
    mares
    0.08
    åĵªä¸ªå¥½
    0.08
    åIJĦèĩªçļĦ
    0.08
    éĥ½å¾Ī好
    0.08
    तर
    0.08
    epat
    0.08
    ì¢Į
    0.08
    ingar
    0.08
    Activations Density 0.001%

    No Known Activations