© 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. 46173
    Prev
    Next
    INDEX
    Explanations

    amino acid mutations

    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
    åĪ¸
    -0.07
    åħ»æ´»
    -0.07
    驳
    -0.07
    ä¸įå¤ĸ
    -0.07
     topped
    -0.06
    æĨ¾
    -0.06
    åĪĨåĮĸ
    -0.06
    aset
    -0.06
    ä¸įå±ij
    -0.06
     contenant
    -0.06
    POSITIVE LOGITS
    positions
    0.08
    è¿İæĿ¥
    0.08
    ä½įç½®ä¸Ĭ
    0.08
     Eck
    0.07
     póź
    0.07
    å±ħéħĴå±ĭ
    0.07
     заменÑĭ
    0.07
    position
    0.07
     positions
    0.07
    è¿İ
    0.07
    Activations Density 0.077%

    No Known Activations