© 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. 60715
    Prev
    Next
    INDEX
    Explanations

    mixing ratio or concentration

    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
    æ¼ıçĶµ
    -0.07
    _WRAP
    -0.07
    Ä©nh
    -0.07
    åĩºåĬ¨
    -0.07
    issan
    -0.07
     abon
    -0.07
    éĿĴåħī
    -0.07
    åħ¶çī¹å¾ģ
    -0.07
    owers
    -0.07
    æİĪæĿĥ
    -0.07
    POSITIVE LOGITS
    ç¨ĢéĩĬ
    0.14
     dil
    0.14
     diluted
    0.12
    dil
    0.11
     Dil
    0.10
    åİŁæľī
    0.08
     volumes
    0.08
     loãng
    0.08
     mixing
    0.08
     volum
    0.07
    Activations Density 0.003%

    No Known Activations