© 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. 13842
    Prev
    Next
    INDEX
    Explanations

    code declarations

    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
    ä¹ħäºĨ
    -0.08
    ither
    -0.07
    æĹ¥ä¹ħ
    -0.07
    Jvm
    -0.07
    avu
    -0.07
    ikt
    -0.07
     ipsum
    -0.07
    客
    -0.07
    çº
    -0.07
     piedi
    -0.07
    POSITIVE LOGITS
    lest
    0.10
    $o
    0.07
    解åĨ³å¥½
    0.07
    (KP
    0.07
    åĸľæ°Ķ
    0.06
    'I
    0.06
    à¸Ĺีà¹Ģà¸Ķียว
    0.06
    stad
    0.06
    chie
    0.06
    æ¢Ń
    0.06
    Activations Density 0.090%

    No Known Activations