© 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. 20914
    Prev
    Next
    INDEX
    Explanations

    ratio, value, domain, costs, table

    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
    çĦ¶å¤§
    -0.09
    scha
    -0.08
    zec
    -0.07
    jik
    -0.07
     Canti
    -0.07
    代ä¹ĭ
    -0.07
    áĥĴáĥĺ
    -0.07
    rene
    -0.07
    luv
    -0.07
    对åħļ
    -0.07
    POSITIVE LOGITS
    天ä¸ĭçļĦ
    0.07
    åĸĶ
    0.07
    ä¸ĢæıIJ
    0.07
    ä¸Ĭè¿°äºĭå®ŀ
    0.07
    éĻ·éĺ±
    0.06
    udge
    0.06
    顺åĪ©å¼Ģå±ķ
    0.06
     }:
    0.06
    ¬
    0.06
     }):
    0.06
    Activations Density 0.010%

    No Known Activations