© 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. 8443
    Prev
    Next
    INDEX
    Explanations

    vs pattern

    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
    emes
    -0.09
    åħĪæĺ¯
    -0.07
    âĢ¦),
    -0.07
    ertos
    -0.07
    è¦ģä¹Ī
    -0.07
    .);
    -0.07
    çĴ¨
    -0.07
    ieves
    -0.07
    enek
    -0.07
    enet
    -0.07
    POSITIVE LOGITS
     vs
    0.14
     versus
    0.10
     VS
    0.09
    åĢ¼å¾Ĺä¸ĢæıIJ
    0.08
    _vs
    0.08
    è¿Ľè¡ĮæŶ
    0.08
    vs
    0.08
    VS
    0.07
    çļĦéĩįè¦ģæĢ§
    0.07
    åıĬåħ¶
    0.07
    Activations Density 0.046%

    No Known Activations