© 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. 10384
    Prev
    Next
    INDEX
    Explanations

    arithmetic and research

    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
    Fit
    -0.07
    (s
    -0.07
     Fit
    -0.06
     Duffy
    -0.06
    dig
    -0.06
    fraction
    -0.06
    壤
    -0.06
    (t
    -0.06
    ouse
    -0.06
     obvious
    -0.06
    POSITIVE LOGITS
    ((&
    0.08
    离ä¸ĸ
    0.08
    ,âĢ¦
    0.08
    æł¼éĩĮ
    0.08
    ()?.
    0.08
    RIES
    0.08
    -thumbnail
    0.08
    oló
    0.07
    ján
    0.07
    .Builder
    0.07
    Activations Density 0.005%

    No Known Activations