© 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. 40394
    Prev
    Next
    INDEX
    Explanations

    error, successfully, timeout, empty

    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
    )':
    -0.08
    "]=>
    -0.08
    "".
    -0.08
    éĻ·
    -0.07
    ÙĨÙĩ
    -0.07
    "":
    -0.07
    bella
    -0.07
    erca
    -0.07
    .'_
    -0.07
    )":
    -0.07
    POSITIVE LOGITS
    !\
    0.10
    请åıĬæŶ
    0.09
    \a
    0.09
    !
    0.08
     prega
    0.08
    请ä¸İ
    0.07
    çĸij
    0.07
    %!
    0.07
     detected
    0.07
    icot
    0.07
    Activations Density 0.144%

    No Known Activations