© 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. 20060
    Prev
    Next
    INDEX
    Explanations

    website urls,code keywords,you + verbs

    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
    foy
    -0.09
    poon
    -0.09
    ä¸ĢæĿ¥
    -0.08
    upro
    -0.08
    éĶ¦æ¶Ľ
    -0.08
    é«ĺ缼
    -0.08
    eturn
    -0.08
    pone
    -0.08
    ornings
    -0.08
    ofire
    -0.08
    POSITIVE LOGITS
    äºĪ
    0.07
    è§Ħ
    0.06
    DT
    0.06
     gan
    0.06
    ä¼ij
    0.06
    èĤĨ
    0.06
     cruc
    0.06
     cap
    0.06
     r
    0.06
    èģĮ
    0.06
    Activations Density 0.001%

    No Known Activations