© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 14929
    Prev
    Next
    INDEX
    Explanations

    eta production

    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
    èĬ±æŀľ
    -0.07
    á»Ļt
    -0.07
    èĶ¥
    -0.06
    èij±
    -0.06
     kisz
    -0.06
    Õ©
    -0.06
    åijĽ
    -0.06
    èįĶ
    -0.06
    vær
    -0.06
    contrib
    -0.06
    POSITIVE LOGITS
    ÑģÑĤÑĢа
    0.08
    ä¸Ńå¿ĥç»Ħ
    0.08
     coron
    0.07
     alde
    0.07
    äºĭ件ä¸Ń
    0.07
    èĪĪ
    0.07
    edicine
    0.07
     chè
    0.07
     cou
    0.07
    亳
    0.07
    Activations Density 0.003%

    No Known Activations