© 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. 17279
    Prev
    Next
    INDEX
    Explanations

    comment lines or code blocks

    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
    è¿ĺæĺ¯éĿŀ常
    -0.09
    çļĦæŶåĢĻä¸Ģå®ļè¦ģ
    -0.08
    év
    -0.08
    éal
    -0.08
    éb
    -0.08
    <|box_end|>
    -0.08
    æv
    -0.07
    ió
    -0.07
    ésp
    -0.07
    лÑĸв
    -0.07
    POSITIVE LOGITS
    Âł
    0.07
    å¿ĥ缮
    0.06
    âĢ
    0.06
    (TM
    0.06
    ਼
    0.06
    PECIAL
    0.06
    åıĮéļıæľº
    0.05
    对æѤä¸įæī¿æĭħä»»ä½ķ
    0.05
    ç»ĵä¸ļ
    0.05
    Selectors
    0.05
    Activations Density 0.041%

    No Known Activations