© 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. 39877
    Prev
    Next
    INDEX
    Explanations

    not possible

    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
    ä½ķå¿ħ
    -0.09
    idez
    -0.08
    trag
    -0.07
    æŶ令
    -0.07
    enance
    -0.07
    ẳng
    -0.07
    asco
    -0.07
    anzia
    -0.07
    .generated
    -0.07
    enso
    -0.07
    POSITIVE LOGITS
    å½ĵä¸Ģ个
    0.07
     truly
    0.07
    羣å¿ĥ
    0.07
    ÙĨاÙģ
    0.07
    avit
    0.06
    ä¹ĭéĹ´çļĦçŁĽçĽ¾
    0.06
    ä¹ĭä¹ħ
    0.06
     fundamentally
    0.06
    _CAP
    0.06
    å¦Ĥæŀľä¸Ģ个
    0.06
    Activations Density 0.002%

    No Known Activations