© 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. 58905
    Prev
    Next
    INDEX
    Explanations

    equivalents or effective size

    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
    æ¾Ī
    -0.08
    atis
    -0.07
    urm
    -0.07
    æĢľ
    -0.07
    .mit
    -0.07
    èĨ©
    -0.07
    MBER
    -0.07
    ophil
    -0.07
    éľĸ
    -0.07
    ׼×ķף
    -0.07
    POSITIVE LOGITS
     equivalent
    0.14
    Equivalent
    0.12
    çŃīæķĪ
    0.12
     Equivalent
    0.11
     equivalents
    0.11
     equivalente
    0.11
    æĬĺåIJĪ
    0.10
     equival
    0.08
    _equiv
    0.08
    æĬĺç®Ĺ
    0.08
    Activations Density 0.021%

    No Known Activations