© 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. 11498
    Prev
    Next
    INDEX
    Explanations

    land, disputes, responds, clinic

    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
    好æĸĩ
    -0.08
    æ·¼
    -0.08
    aurant
    -0.08
    isle
    -0.08
    isbury
    -0.07
    inkel
    -0.07
    -await
    -0.07
    hern
    -0.07
    EGIN
    -0.07
    iette
    -0.07
    POSITIVE LOGITS
    ogg
    0.06
    å½¢
    0.06
     volta
    0.06
    æĥ³å¾ĹåĪ°
    0.06
     accom
    0.06
    ä¸įè¶ħè¿ĩ
    0.06
    åı¯æĮī
    0.06
    æĹłæŃ¢å¢ĥ
    0.06
     ï
    0.06
    ÙĤا
    0.06
    Activations Density 0.006%

    No Known Activations