© 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. 42774
    Prev
    Next
    INDEX
    Explanations

    protocol identifiers

    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
    çijŀ
    -0.07
     familiar
    -0.07
    è¶ħ
    -0.06
    ipt
    -0.06
    æijĩ头
    -0.06
     wel
    -0.06
     sÃŃ
    -0.06
     cname
    -0.06
    à¹Ģรà¸Ļ
    -0.06
     regr
    -0.06
    POSITIVE LOGITS
    stein
    0.08
    åIJįæĢĿ
    0.08
    Ñİд
    0.08
    _coin
    0.08
     СооÑĤвеÑĤÑģÑĤвенно
    0.08
    å®ģå¸Ĥ
    0.07
    oga
    0.07
    /dom
    0.07
    ABCDEFGHI
    0.07
     Duch
    0.07
    Activations Density 0.187%

    No Known Activations