© 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. 10374
    Prev
    Next
    INDEX
    Explanations

    divisible, -able, -ible suffixes

    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
    ogra
    -0.08
    elten
    -0.08
    uari
    -0.08
    åĪĨæĶ¯
    -0.08
    å°±è¶Ĭ
    -0.07
     }>
    -0.07
    æ°Ľ
    -0.07
    ecraft
    -0.07
    æĪijè¦ģè¯Ħ论
    -0.07
     Grau
    -0.07
    POSITIVE LOGITS
    ä¸įæĿ¥
    0.07
    isable
    0.07
    Ïĩη
    0.07
    ducible
    0.06
    izable
    0.06
    æĿ¥ä¹ĭ
    0.06
    ieke
    0.06
     originating
    0.06
    æ¾Ħ
    0.06
    å¾ĹæĿ¥
    0.06
    Activations Density 0.030%

    No Known Activations