© 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. 38293
    Prev
    Next
    INDEX
    Explanations

    annular, concentric, inner, outer, radius, diameter

    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
    åĢ¾
    -0.07
    åijĨ
    -0.07
    orf
    -0.06
    çļĪ
    -0.06
    æİ¢
    -0.06
    çĶŁåĬ¨
    -0.06
    缸åħ³æĢ§
    -0.06
    abilia
    -0.06
    端æŃ£
    -0.06
    çĬ¶æĢģ
    -0.06
    POSITIVE LOGITS
    å¤ĸå¾Ħ
    0.09
     concent
    0.09
    åIJĮå¿ĥ
    0.09
    -radius
    0.09
     radius
    0.09
    åľĪ
    0.08
     radial
    0.08
    æĪijçļĦ书æŀ¶
    0.08
    radius
    0.08
    -ring
    0.08
    Activations Density 0.017%

    No Known Activations