© 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. 49001
    Prev
    Next
    INDEX
    Explanations

    shape, structure, variation, evolution

    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
    pä
    -0.08
    caff
    -0.08
    rote
    -0.08
    _DEFIN
    -0.08
     ruj
    -0.07
    asco
    -0.07
    ÙģاÙĤ
    -0.07
    .googleapis
    -0.07
    acea
    -0.07
    stinian
    -0.07
    POSITIVE LOGITS
     spontaneous
    0.11
    åģı好
    0.10
     spontaneously
    0.10
    åĢ¾åIJijäºİ
    0.10
    èĩªåıij
    0.10
    åıįæĺłäºĨ
    0.09
    è¶ĭåIJij
    0.09
     tendency
    0.09
    åĢ¾åIJij
    0.08
     preferences
    0.08
    Activations Density 0.121%

    No Known Activations