© 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. 58153
    Prev
    Next
    INDEX
    Explanations

    code comments and examples

    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
    $a
    -0.06
    åĪĨåŃIJ
    -0.06
    pec
    -0.06
    ä»İä¸Ģ个
    -0.06
    -R
    -0.06
    itra
    -0.06
    ilar
    -0.06
    oley
    -0.06
    ê
    -0.06
    éĻ©
    -0.06
    POSITIVE LOGITS
    åĨħç»ı
    0.08
    çĻ¾åıĺ
    0.07
    ông
    0.07
     solcher
    0.07
    èī²åĪĹ
    0.07
    sburg
    0.07
    eil
    0.07
    oha
    0.07
    anya
    0.07
    ensión
    0.07
    Activations Density 0.001%

    No Known Activations