© 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. 61413
    Prev
    Next
    INDEX
    Explanations

    legally or affiliate

    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
    èĮĥåĽ´ä¹ĭåĨħ
    -0.08
    oon
    -0.07
    ç»ĵæĿŁä¹ĭåIJİ
    -0.07
    stw
    -0.07
    cope
    -0.07
    è²Ķ
    -0.07
    èĩªè¡ĮæıIJä¾Ľ
    -0.07
    engo
    -0.07
    è¿ĶåĽŀ缮å½ķ
    -0.07
    NTAX
    -0.07
    POSITIVE LOGITS
    ä¹ĺ
    0.08
    arit
    0.07
    svar
    0.07
    使å®ĥ
    0.07
    aby
    0.07
     legally
    0.07
     transforming
    0.07
    åħ¨ä½ĵ
    0.06
    à¹Ģà¸ŀิà¹Īม
    0.06
    SMART
    0.06
    Activations Density 0.003%

    No Known Activations