© 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. 51850
    Prev
    Next
    INDEX
    Explanations

    every, fully, totally, all

    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
     except
    -0.10
    Except
    -0.09
    éĻ¤äºĨ
    -0.09
    éĻ¤äºĨåľ¨
    -0.09
     Except
    -0.08
    éĻ¤éĿŀ
    -0.08
    except
    -0.08
     unless
    -0.07
     Unless
    -0.07
    Unless
    -0.07
    POSITIVE LOGITS
    odar
    0.08
    ä¹Łå¹¶ä¸į
    0.08
    äºijéľĦ
    0.08
    èĻ½çĦ¶ä»ĸ
    0.08
    aviour
    0.07
     Ñĥж
    0.07
    ä½Ĩèĩ³å°ij
    0.07
    ebes
    0.07
    ãĤ¹ãĤ¯
    0.07
    colar
    0.07
    Activations Density 0.211%

    No Known Activations