© 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. 47724
    Prev
    Next
    INDEX
    Explanations

    isotopes

    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
    åŁĶ
    -0.09
    åħħè¡Ģ
    -0.09
    æĴijèµ·
    -0.08
     Berb
    -0.07
    óc
    -0.07
    èµĦä¿¡
    -0.07
    ttl
    -0.07
    èĩªç«ĭ
    -0.07
    åħ¬å®³
    -0.07
    ðŁĴ
    -0.07
    POSITIVE LOGITS
     geo
    0.08
     analyses
    0.08
    åĮĻ
    0.07
    witter
    0.07
    微信æľĭåıĭåľĪ
    0.07
     swinger
    0.07
     signatures
    0.07
    åĪĨæŀIJ仪
    0.07
    Geo
    0.07
    åŁºæºĸ
    0.07
    Activations Density 0.039%

    No Known Activations