© 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. 58504
    Prev
    Next
    INDEX
    Explanations

    rearrange, reshape, transpose

    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
    å·®åĪĨ
    -0.08
    ä»°æľĽ
    -0.07
     tied
    -0.07
    æĹ¥åĪ¶
    -0.07
    æŃ¢
    -0.07
    èĩªæĪij
    -0.07
    èĩªå°Ĭ
    -0.07
     differential
    -0.07
    ä»°
    -0.07
    graphql
    -0.06
    POSITIVE LOGITS
     rearr
    0.11
     reordered
    0.08
     reorder
    0.08
    éĩįå¡ij
    0.08
    rames
    0.08
    ç½Ĺæ±ī
    0.07
     interchange
    0.07
    osz
    0.07
    adera
    0.07
    移åĬ¨
    0.07
    Activations Density 0.004%

    No Known Activations