© 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. 57493
    Prev
    Next
    INDEX
    Explanations

    M, R, x, μ, speed

    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
    allee
    -0.06
    Wel
    -0.06
    æĶ¯
    -0.06
    ละ
    -0.06
     Berliner
    -0.06
    جاÙĩ
    -0.06
    ophilia
    -0.06
    åħħè¡Ģ
    -0.06
    åIJ¬
    -0.05
     straf
    -0.05
    POSITIVE LOGITS
    ueur
    0.09
    窦
    0.08
    intes
    0.08
     conveniente
    0.07
    çļĦæłĩåĩĨ
    0.07
    éĥ¨éŨèģĶåIJĪ
    0.07
    aku
    0.07
    æĪijåIJ§
    0.07
    好货
    0.07
    æłĩåĩĨè¦ģæ±Ĥ
    0.07
    Activations Density 0.003%

    No Known Activations