© 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. 34569
    Prev
    Next
    INDEX
    Explanations

    CDDL, Oracle, New Jersey, copyright

    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
     Bangkok
    -0.09
    éĬĢ座
    -0.09
    æĽ¼è°·
    -0.08
    æį·åħĭ
    -0.08
    å®Ŀå®ī
    -0.08
     Budapest
    -0.08
     ЦСÐļÐIJ
    -0.08
    åłª
    -0.08
    åĤ¾åIJij
    -0.08
    éĢļå·ŀ
    -0.08
    POSITIVE LOGITS
    éĹ½
    0.12
    Oracle
    0.11
    æ°¸åĺī
    0.11
     Colombian
    0.10
     Oracle
    0.10
    ç¦ı建çľģ
    0.10
     colombiano
    0.10
    å®ģå¾·
    0.10
    æŃ¦å¤·
    0.10
     δ
    0.10
    Activations Density 0.897%

    No Known Activations