© 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. 25393
    Prev
    Next
    INDEX
    Explanations

    journal citation details

    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
    -relative
    -0.09
    ÐķС
    -0.07
    arpa
    -0.07
    omad
    -0.07
    ä¹Ŀåįģ
    -0.07
    opup
    -0.07
    lope
    -0.07
    azor
    -0.07
    èµĶ
    -0.07
     thang
    -0.07
    POSITIVE LOGITS
     fas
    0.06
     Tow
    0.06
    laus
    0.06
    èĬľ
    0.06
     (_)
    0.06
    ÑĢиÑĤе
    0.06
    åĮĻ
    0.06
    вле
    0.06
    æ³ģ
    0.06
    ouser
    0.06
    Activations Density 0.025%

    No Known Activations