© 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. 19538
    Prev
    Next
    INDEX
    Explanations

    Authorize Purchases

    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
     Uncomment
    -0.06
    ä¸įæĩĪåĬªåĬĽ
    -0.06
    两大
    -0.06
    %
    -0.06
    Âł
    -0.06
    2
    -0.06
    9
    -0.06
    8
    -0.06
     inv
    -0.06
    åIJĦç§ij
    -0.06
    POSITIVE LOGITS
     **—
    0.10
    åĽ½ç¾İ
    0.08
    âĢ¦the
    0.08
    åŃ£åIJİ
    0.08
    º¼
    0.08
     insomma
    0.08
    ustral
    0.08
    èĢĥ究
    0.08
    以ä¸ĭåĩłä¸ªæĸ¹éĿ¢
    0.08
    éģµå®ĪåĽ½å®¶
    0.08
    Activations Density 0.002%

    No Known Activations