© 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. 47791
    Prev
    Next
    INDEX
    Explanations

    written works

    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
    notated
    -0.08
    è¶ħè¿ĩ约
    -0.08
    å®ŀå¤Ħ
    -0.08
    ÏĦίαÏĤ
    -0.08
    /vendors
    -0.08
    samp
    -0.08
    çİīæłij
    -0.07
    æıĥ
    -0.07
    ereum
    -0.07
    plib
    -0.07
    POSITIVE LOGITS
     titled
    0.09
     entitled
    0.08
    åIJį为
    0.08
    ster
    0.07
     berjudul
    0.07
    åı«åģļ
    0.07
     called
    0.07
     on
    0.07
    åı«
    0.07
    -length
    0.07
    Activations Density 0.646%

    No Known Activations