© 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. 51221
    Prev
    Next
    INDEX
    Explanations

    #include or <!--[

    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
    ÐĶÐIJÐł
    -0.07
    æľ¬ç«ĻåĨħ容
    -0.07
    StringLength
    -0.07
    itera
    -0.07
    ãĥķãĥ©ãĥ¯ãĥ¼
    -0.07
    ese
    -0.07
    ÏĦεÏħ
    -0.06
     Baik
    -0.06
    ondag
    -0.06
    erness
    -0.06
    POSITIVE LOGITS
    engel
    0.07
    翼
    0.07
     Lam
    0.07
    ç§ī
    0.07
    åįĸç»Ļ
    0.07
     rever
    0.07
    erra
    0.07
    å¢ħ
    0.06
    rever
    0.06
    achen
    0.06
    Activations Density 0.001%

    No Known Activations