© 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. 25961
    Prev
    Next
    INDEX
    Explanations

    India, Felix, Chrysler, Vampire, leadership

    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
    çļĦæĺ¯
    -0.08
    çļĦäººåľ¨
    -0.07
    åľĪçļĦ
    -0.07
     }}/
    -0.06
    obili
    -0.06
    )e
    -0.06
    åıijå±ķåĴĮ
    -0.06
    çļĦåıijå±ķåĴĮ
    -0.06
    çļĦéĤ£å¤©
    -0.06
    ä¸ĭåĪ°
    -0.06
    POSITIVE LOGITS
    å°ıæķħäºĭ
    0.08
    该æĢİä¹ĪåĬŀ
    0.08
    详æĥħ请
    0.08
    zal
    0.07
    çĦ¶å¤§
    0.07
    该æĢİä¹Ī
    0.07
    æĶ¶èĹıæľ¬ç«Ļ
    0.07
    ä½ľåĵģåĨħ容
    0.07
     obstante
    0.07
    .Exists
    0.07
    Activations Density 0.037%

    No Known Activations