© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 4686
    Prev
    Next
    INDEX
    Explanations

    consider and call variations

    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
    Negative Logits
    sche
    -0.07
    eke
    -0.07
    scha
    -0.07
    mey
    -0.07
    ijIJ
    -0.07
    ืà¸Ļ
    -0.06
    vier
    -0.06
    itest
    -0.06
    plätze
    -0.06
    åľ¨æľ¬
    -0.06
    POSITIVE LOGITS
    åħ¶ä¸º
    0.13
    æŃ¤ä¸º
    0.12
    è§Ĩ为
    0.12
    å®ĥ为
    0.12
    è§Ĩä½ľ
    0.11
    è¦ĸçĤº
    0.11
    è¿Ļæĺ¯ä¸Ģåľº
    0.10
    èªī为
    0.10
    çľĭä½ľæĺ¯
    0.10
    çķ¶ä½ľ
    0.10
    Activations Density 0.141%

    No Known Activations