© 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. 40212
    Prev
    Next
    INDEX
    Explanations

    code symbols and special characters

    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
    ollo
    -0.06
    otte
    -0.06
    ikov
    -0.06
    yno
    -0.06
    brace
    -0.06
    å°ıæ¡¥
    -0.06
    è´Łè´£äººè¡¨ç¤º
    -0.06
     Cash
    -0.06
    ãģ¨ãĤĤ
    -0.06
    gne
    -0.06
    POSITIVE LOGITS
     sonstige
    0.10
     egyéb
    0.09
    åħ¶å®ĥ
    0.09
     инÑĭÑħ
    0.08
    ä»»ä½ķåħ¶ä»ĸ
    0.08
    éĺħè¯»æľ¬æĸĩåīį
    0.08
    à¸Ńืà¹Īà¸Ļà¹Ĩ
    0.08
    åħ¶ä»ĸçļĦ
    0.07
    ãģĿãģ®ä»ĸãģ®
    0.07
     downright
    0.07
    Activations Density 0.453%

    No Known Activations