© 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. 65259
    Prev
    Next
    INDEX
    Explanations

    rounding decimal places or picking without replacement

    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
    ritch
    -0.06
    accio
    -0.06
    اÙħØ©
    -0.06
    acci
    -0.06
    ä»ĸ们认为
    -0.06
    Åijt
    -0.06
     pues
    -0.05
     or
    -0.05
    ÙģØ©
    -0.05
    itz
    -0.05
    POSITIVE LOGITS
    ):-
    0.08
    (&$
    0.08
    ahu
    0.07
    antil
    0.07
    uffle
    0.07
    渡åģĩ
    0.07
    addir
    0.07
    aksin
    0.07
    rieved
    0.07
    xeb
    0.07
    Activations Density 0.009%

    No Known Activations