© 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. 58297
    Prev
    Next
    INDEX
    Explanations

    2, b, h

    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
    ä¸į失
    -0.07
    WithContext
    -0.07
    èĤ¯
    -0.07
    çĻ»
    -0.06
    "$
    -0.06
    лама
    -0.06
    ä¹ħ
    -0.06
    ken
    -0.06
    [class
    -0.06
     digitally
    -0.06
    POSITIVE LOGITS
    uge
    0.07
    (rowIndex
    0.07
    iners
    0.07
    زار
    0.07
    peater
    0.07
    igue
    0.07
    åŃĺåľ¨ä¸Ģå®ļçļĦ
    0.07
    éĹ®åĮ»çĶŁ
    0.07
    zeg
    0.07
    ary
    0.07
    Activations Density 0.044%

    No Known Activations