© 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. 31217
    Prev
    Next
    INDEX
    Explanations

    procedure, data, regulation, intact

    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
    maz
    -0.08
    _corner
    -0.07
    幸
    -0.07
    èĥĮ
    -0.07
    abies
    -0.07
    Ñħла
    -0.07
    è¶ħåķĨ
    -0.07
    _slots
    -0.07
    аж
    -0.07
    æļ«
    -0.07
    POSITIVE LOGITS
    اصÙĦ
    0.08
    åĪ«æľī
    0.07
    uard
    0.07
    å°Ķ夫
    0.06
    uas
    0.06
    æľŁæ»¡åIJİ
    0.06
    ilda
    0.06
    olid
    0.06
    æĶ¹æĪIJ
    0.06
    åıĮèĬĤ
    0.06
    Activations Density 0.664%

    No Known Activations