© 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. 38827
    Prev
    Next
    INDEX
    Explanations

    ratio, relationship, relation

    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
     اÙĦتÙħ
    -0.08
    agi
    -0.07
    udad
    -0.07
    veu
    -0.07
    _vlog
    -0.07
    etu
    -0.07
    第ä¸Ģåį°è±¡
    -0.07
    çĶ³æĬ¥æĿIJæĸĻ
    -0.07
     Herrn
    -0.07
    isht
    -0.07
    POSITIVE LOGITS
     ratio
    0.11
     relationship
    0.09
     Ratio
    0.09
    æ¯Ķä¾ĭ
    0.09
     ratios
    0.09
    çļĦæ¯Ķä¾ĭ
    0.09
    åħ³ç³»
    0.09
    åĢįæķ°
    0.08
    Ratio
    0.08
    çļĦåħ³ç³»
    0.08
    Activations Density 0.001%

    No Known Activations