© 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. 46853
    Prev
    Next
    INDEX
    Explanations

    density and phases

    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
    åıĬè¦ģæ±Ĥ
    -0.08
    mozilla
    -0.07
    éķ¿ç¯ĩ
    -0.07
    วà¸Ļ
    -0.07
    åħijçİ°
    -0.07
    æĪĸå¤ļ
    -0.07
    .Constraint
    -0.07
    æĮīéľĢ
    -0.07
    olz
    -0.07
    èĶĵ
    -0.07
    POSITIVE LOGITS
    大å¤ļæķ°
    0.08
    ä½İäºİ
    0.08
     (>
    0.08
     heavier
    0.08
    é«ĺäºİ
    0.07
     grav
    0.07
     lighter
    0.07
    esel
    0.07
    å¤ļæķ°
    0.07
    éĩįçļĦ
    0.07
    Activations Density 0.003%

    No Known Activations