© 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. 61518
    Prev
    Next
    INDEX
    Explanations

    ref, populations, lazy, disabled

    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
    antina
    -0.08
    íĺ¼
    -0.07
    á»ĩ
    -0.07
    åį³çĶ¨
    -0.07
    æĢ»æľīä¸Ģ天
    -0.07
    ูà¸Ķ
    -0.07
     diman
    -0.06
    dain
    -0.06
    -plugins
    -0.06
    _CTX
    -0.06
    POSITIVE LOGITS
     qualifier
    0.09
     qualities
    0.09
     qualific
    0.09
     qualifies
    0.09
    classify
    0.08
    ä»Ģä¹Īåı«
    0.08
     classification
    0.08
    åĪĨç±»
    0.08
    åħ³éĶ®è¯į
    0.08
     characteristics
    0.08
    Activations Density 0.203%

    No Known Activations