© 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. 57719
    Prev
    Next
    INDEX
    Explanations

    possessive its noun

    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
    åħ¶åİŁåĽł
    -0.07
     Dinge
    -0.07
    hawk
    -0.07
    esti
    -0.07
    äºĭçī©çļĦ
    -0.07
    eur
    -0.07
    ìĦľëĬĶ
    -0.07
    ease
    -0.06
    oose
    -0.06
    oord
    -0.06
    POSITIVE LOGITS
    /her
    0.15
     own
    0.14
    ä¿©
    0.13
    lef
    0.12
    clf
    0.10
    inerary
    0.10
    SELF
    0.10
    åĢĨ
    0.10
    ä¸ŃåĽ½å®¶
    0.10
     behalf
    0.10
    Activations Density 0.113%

    No Known Activations