© 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. 45899
    Prev
    Next
    INDEX
    Explanations

    the [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¶ä¸ŃçļĦ
    -0.08
    ä¸ĭåĪ°
    -0.08
    antro
    -0.08
    è
    -0.07
    åħĭ森
    -0.07
    odge
    -0.07
    OnClick
    -0.07
    ä¹ŁæĬĬ
    -0.07
    ложи
    -0.07
    æīĢ欲
    -0.07
    POSITIVE LOGITS
     behalf
    0.23
     ÙĪعÙĦÙī
    0.14
     occasion
    0.13
     пÑĢоÑĤÑıжении
    0.12
     basis
    0.11
     ÑįÑĤапе
    0.11
     keresztül
    0.11
     whim
    0.11
    eness
    0.10
     اÙĦرغÙħ
    0.10
    Activations Density 0.763%

    No Known Activations