© 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. 30765
    Prev
    Next
    INDEX
    Explanations

    eardrum, chocolate, snails, frozen, textbox, scope, chips

    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
    versammlung
    -0.08
    æģįæĥļ
    -0.08
    asia
    -0.07
    aux
    -0.07
    æľŁå¾ħçĿĢ
    -0.07
     Laure
    -0.07
    æŃ¹
    -0.07
    ä¸ĭæľī
    -0.06
    bons
    -0.06
    å³Ļ
    -0.06
    POSITIVE LOGITS
    èĢģçĻ¾å§ĵ
    0.08
    |i
    0.07
    adena
    0.06
    æĹ¥å¸¸çĶŁæ´»ä¸Ń
    0.06
    nado
    0.06
    -like
    0.06
    [group
    0.06
    ç¶ģ
    0.06
    碧çİī
    0.06
    .EX
    0.06
    Activations Density 0.477%

    No Known Activations