© 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. 47871
    Prev
    Next
    INDEX
    Explanations

    except

    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
    emm
    -0.08
    ä¸į失
    -0.07
    ä¸įæĶ¾
    -0.06
    ans
    -0.06
    çŃĸ
    -0.06
     instante
    -0.06
    æħµ
    -0.06
    两ä¸į误
    -0.06
    VS
    -0.06
    edi
    -0.06
    POSITIVE LOGITS
    etos
    0.11
     âĿ
    0.10
    éĻ¤å¤ĸ
    0.09
    缺å°ij
    0.08
    cluded
    0.08
    æİĴéĻ¤
    0.08
     manca
    0.08
    âĿ
    0.08
    å°Ķåħĭ
    0.08
    ë¹¼
    0.08
    Activations Density 0.009%

    No Known Activations