© 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. 14181
    Prev
    Next
    INDEX
    Explanations

    two recalls of

    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
    oyer
    -0.09
    æī¿æĭħä¸ĢåĪĩ
    -0.08
    zee
    -0.07
    å¼Ĥä½į
    -0.07
    _TRACE
    -0.07
    идÑĥ
    -0.07
    iagnostics
    -0.07
    alytics
    -0.07
    .fromString
    -0.07
    å½ĵåľº
    -0.07
    POSITIVE LOGITS
    æķ°æ¬¡
    0.20
    两次
    0.19
    ä¸ī次
    0.19
    åĩłæ¬¡
    0.19
    åĽĽæ¬¡
    0.17
    åħ©æ¬¡
    0.17
    äºĶ次
    0.17
    æ¯ı次
    0.16
    ä¸Ģ次
    0.16
    å¤ļ次
    0.16
    Activations Density 0.536%

    No Known Activations