© 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. 3297
    Prev
    Next
    INDEX
    Explanations

    cer. article. quote

    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
    اÙħر
    -0.08
    æĹ¥çĶŁ
    -0.07
    rog
    -0.07
    å¤§æľ¬
    -0.07
    anic
    -0.06
    çŁ¥åħ¶
    -0.06
    æĮĩ纹
    -0.06
    å±±ä¸ĭ
    -0.06
    —even
    -0.06
    jas
    -0.06
    POSITIVE LOGITS
    .cx
    0.07
    ÅŁa
    0.07
    iola
    0.07
    èĬ¯
    0.07
     ÙĦÙĦÙĩ
    0.07
    ÑĩÑĥк
    0.06
     pia
    0.06
    =read
    0.06
    ssi
    0.06
    è´°
    0.06
    Activations Density 0.009%

    No Known Activations