© 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. 41450
    Prev
    Next
    INDEX
    Explanations

    mathematical vectors and notation

    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
    éĻIJäºİ
    -0.07
    äne
    -0.07
    çŃĭ
    -0.07
    è°Īç¬ij
    -0.07
    æĿ¡ä»¶æĺ¯
    -0.06
     condition
    -0.06
    ä¸ĭæ°´
    -0.06
    åIJĮç±»
    -0.06
    Dest
    -0.06
    çļĦåŃĺåľ¨
    -0.06
    POSITIVE LOGITS
    çĽ¸ä¿¡èĩªå·±
    0.08
    ucas
    0.08
    armi
    0.08
    èĩªå·²
    0.08
    asily
    0.08
    гада
    0.08
    autore
    0.07
    夷
    0.07
    åį«
    0.07
    æĿŁ
    0.07
    Activations Density 0.010%

    No Known Activations