© 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. 48618
    Prev
    Next
    INDEX
    Explanations

    circuit

    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
    èĮ¬
    -0.08
    coni
    -0.08
    afil
    -0.08
    asher
    -0.07
    æĥ®
    -0.07
    èĩªæĭĶ
    -0.07
    engi
    -0.07
    erien
    -0.07
    æİ¥ä¸ĭ
    -0.07
    æŃ»äºĨ
    -0.07
    POSITIVE LOGITS
    éĺ³
    0.06
    åıĪ
    0.06
    èݱ
    0.06
    æ¯ĶåĪ©
    0.06
    æ°´å¹³
    0.06
    letz
    0.06
    éĹ
    0.06
     ent
    0.06
    éģĩ
    0.06
     places
    0.06
    Activations Density 0.466%

    No Known Activations