© 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. 26409
    Prev
    Next
    INDEX
    Explanations

    geometric shapes and spatial arrangements

    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
    .Zero
    -0.07
    fresh
    -0.07
    har
    -0.07
    æ®Ĭ
    -0.07
    ç»Ī身
    -0.06
    lease
    -0.06
    éļı身æIJºå¸¦
    -0.06
     relevant
    -0.06
    éļı身
    -0.06
    åħ·
    -0.06
    POSITIVE LOGITS
    ocop
    0.09
    ertools
    0.09
    :\/\/
    0.09
    ä¸Ģ女
    0.09
    诽
    0.09
    боÑĢо
    0.09
    trup
    0.08
    å½¢æĪIJä¸Ģ个
    0.08
    æĬĬä¸Ģ个
    0.08
    opleft
    0.08
    Activations Density 0.014%

    No Known Activations