© 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. 13235
    Prev
    Next
    INDEX
    Explanations

    technical programming concepts

    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
    åıĬåħ¶ä»ĸ
    -0.08
    æĪĸåħ¶ä»ĸ
    -0.07
    以åıĬåħ¶ä»ĸ
    -0.07
    æĪĸåħ¶å®ĥ
    -0.06
    -ever
    -0.06
    ä¹Łä¸įæķ¢
    -0.06
    使çĶ¨åĴĮ
    -0.06
    äºĨä¹Ī
    -0.06
    ½ij
    -0.06
    åıĬåħ¶å®ĥ
    -0.06
    POSITIVE LOGITS
    èĢĮä¸įæĺ¯
    0.11
    èĢĮéĿŀ
    0.10
     rather
    0.10
    rather
    0.08
    å¤§åĽ½
    0.08
    iverse
    0.08
    èĢĮéĻį
    0.08
    FromArray
    0.07
     ÙĪÙĦÙĬ
    0.07
     chứ
    0.07
    Activations Density 0.181%

    No Known Activations