© 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. 22996
    Prev
    Next
    INDEX
    Explanations

    on the other hand

    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
    èĢĮä¸įæĺ¯
    -0.09
    èĢĮæľª
    -0.08
    èĢĮä¸į
    -0.08
    èĢĮéĿŀ
    -0.08
    aland
    -0.07
    èIJĿ
    -0.07
    人ä¸ĸ
    -0.07
    ual
    -0.07
    orie
    -0.07
    erez
    -0.07
    POSITIVE LOGITS
     hingegen
    0.09
    亦çĦ¶
    0.09
     dagegen
    0.09
     theirs
    0.09
     наобоÑĢоÑĤ
    0.09
    åIJİèĢħ
    0.08
    缸åıį
    0.08
    åĪĻ以
    0.08
     sebaliknya
    0.08
    åīĩæĺ¯
    0.08
    Activations Density 0.026%

    No Known Activations