© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 22627
    Prev
    Next
    INDEX
    Explanations

    cyclopropane

    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
    amble
    -0.07
    碧
    -0.06
    æ»ĭ
    -0.06
     elo
    -0.06
    å°Ĭæķ¬
    -0.06
    à¸Ĺà¹Īวม
    -0.06
    æ®·
    -0.06
     alphanumeric
    -0.06
    éģ®èĶ½
    -0.06
    èĥĮå½±
    -0.06
    POSITIVE LOGITS
    วà¸ĩ
    0.08
     극복
    0.07
    çĻ¾å²ģ
    0.07
    çŁ¯æŃ£
    0.07
    驱车
    0.07
    otomy
    0.07
     пÑĢоÑĩноÑģÑĤÑĮ
    0.07
    /tiny
    0.07
     ÙħÙĨتشر
    0.07
    çݯ
    0.07
    Activations Density 0.008%

    No Known Activations