© 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. 63640
    Prev
    Next
    INDEX
    Explanations

    ranks, DNA, volume, value, index

    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
    éĢļåĪĻ
    -0.09
     Folg
    -0.08
    )&&
    -0.07
    æĺ¾å¾®
    -0.07
    gur
    -0.07
    gart
    -0.07
    .capitalize
    -0.07
    راÙĩ
    -0.06
    osa
    -0.06
    å¯Ĥ
    -0.06
    POSITIVE LOGITS
    åı¯çĶ¨äºİ
    0.13
    çĶ¨äºİ
    0.13
    以便äºİ
    0.10
    åı¯ä»¥çĶ¨äºİ
    0.10
    以å¤ĩ
    0.10
    used
    0.10
    çĶ¨æĸ¼
    0.10
     Used
    0.09
    以便
    0.09
    å¤ĩçĶ¨
    0.09
    Activations Density 0.607%

    No Known Activations