© 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. 26444
    Prev
    Next
    INDEX
    Explanations

    probability of sequence

    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
    xa
    -0.07
     Pike
    -0.07
    èģĮ
    -0.06
    amt
    -0.06
    ins
    -0.06
    æĮĤåľ¨
    -0.06
    data
    -0.06
    èĥĮ离
    -0.06
     Buffered
    -0.06
    roda
    -0.06
    POSITIVE LOGITS
    clare
    0.08
    ×¢×Ļ
    0.08
    æ¡ĵ
    0.07
    å°¾
    0.07
    ä¸ĢæĮĩ
    0.07
    è½¼
    0.07
    ancell
    0.07
    ernes
    0.07
    geld
    0.07
    apan
    0.07
    Activations Density 0.008%

    No Known Activations