© 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. 44114
    Prev
    Next
    INDEX
    Explanations

    smooth manifold/vector field

    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
     lagun
    -0.10
    ɵ
    -0.09
     Fitness
    -0.09
    gat
    -0.09
    inig
    -0.09
    òng
    -0.08
    转åIJijçģ¯
    -0.08
    casting
    -0.08
    çľĭåľ¨
    -0.08
    éĥģéĹ·
    -0.08
    POSITIVE LOGITS
    å°ĺ
    0.07
    -ul
    0.07
     hyper
    0.06
     taper
    0.06
     dust
    0.06
     شع
    0.06
    uw
    0.06
     Sa
    0.06
     Hyper
    0.06
    finite
    0.06
    Activations Density 0.004%

    No Known Activations