© 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. 32193
    Prev
    Next
    INDEX
    Explanations

    programming initialization parameters

    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
    为她
    -0.07
     $
    -0.07
    å®īçIJª
    -0.07
     she
    -0.06
    espo
    -0.06
     ее
    -0.06
    对她
    -0.06
    ugo
    -0.06
    éĹ®å¥¹
    -0.06
     еÑij
    -0.06
    POSITIVE LOGITS
    ombat
    0.10
    å°įä»ĸ
    0.09
    åĪ°ä»ĸ
    0.09
    å°Ĩä»ĸ
    0.09
    his
    0.09
    Injector
    0.09
    ç»Ļä»ĸçļĦ
    0.08
    ä¸Ī
    0.08
    rire
    0.08
    è®ĵä»ĸ
    0.08
    Activations Density 1.244%

    No Known Activations