© 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. 26994
    Prev
    Next
    INDEX
    Explanations

    following introductory phrases

    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
    дини
    -0.07
    amps
    -0.07
     mic
    -0.06
     Impress
    -0.06
    iki
    -0.06
    κι
    -0.06
    elo
    -0.06
     nothing
    -0.06
    å
    -0.06
    rr
    -0.06
    POSITIVE LOGITS
    ä¹ĭå®Ŀ
    0.08
    æĪĸå¤ļ个
    0.08
    mén
    0.07
    OPP
    0.07
    æŶéľĢè¦ģ
    0.07
    éĶĻé¢ĺ
    0.07
    াদà§ĩর
    0.07
    å¨Ħ
    0.07
     vario
    0.07
    æŶæīĢ
    0.07
    Activations Density 0.005%

    No Known Activations