© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 16235
    Prev
    Next
    INDEX
    Explanations

    aggregating and averaging values

    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
     Fur
    -0.07
    decl
    -0.07
    lyn
    -0.07
     szint
    -0.06
    ÑģÑĤоиÑĤ
    -0.06
    次çļĦ
    -0.06
    åĪĨåĪ«ä¸º
    -0.06
    æ²»çIJĨ
    -0.06
    eng
    -0.06
    enge
    -0.06
    POSITIVE LOGITS
     across
    0.11
    åľ¨æīĢæľī
    0.09
    对æīĢæľī
    0.09
     Across
    0.09
    Across
    0.09
    æīĢæľī
    0.09
    æīĢæľīåĨħ容
    0.08
    çİĭæµ·
    0.08
    ĥ½
    0.08
     over
    0.08
    Activations Density 0.005%

    No Known Activations