© 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. 18399
    Prev
    Next
    INDEX
    Explanations

    non-linear function

    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
    isl
    -0.07
    imposta
    -0.07
     Dunn
    -0.07
    æ¬
    -0.07
    adows
    -0.07
    uck
    -0.06
    afia
    -0.06
    ove
    -0.06
    åѦçĶŁå®¶éķ¿
    -0.06
    obil
    -0.06
    POSITIVE LOGITS
    äºĭå®ŀè¯ģæĺİ
    0.08
    æĺ±
    0.08
    expr
    0.07
    تÙħ
    0.07
    ype
    0.07
    antz
    0.07
     funcs
    0.07
    äºĭå®ŀ
    0.07
    æŀŃ
    0.07
    etic
    0.07
    Activations Density 0.010%

    No Known Activations