© 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. 29589
    Prev
    Next
    INDEX
    Explanations

    parts and fold

    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
    reiber
    -0.07
    /react
    -0.07
    以åıĬ
    -0.07
    ä¸ĭè¿°
    -0.07
    .ready
    -0.07
    -but
    -0.06
    âĢ¦**
    -0.06
    воз
    -0.06
    æľ¬æ³ķ
    -0.06
    **!
    -0.06
    POSITIVE LOGITS
    åĨĴ
    0.08
    åħ³æ³¨åĴĮ
    0.07
    ungk
    0.07
    çĶ²çŃī
    0.07
    amient
    0.06
    rones
    0.06
    éĢĴ
    0.06
    GED
    0.06
    è¯ģæį®è¯ģæĺİ
    0.06
    足çļĦ
    0.06
    Activations Density 0.009%

    No Known Activations