© 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. 41308
    Prev
    Next
    INDEX
    Explanations

    should/would followed by action verbs

    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
     бÑĥдÑĤо
    -0.08
    ukah
    -0.08
    è¿ĶåĽŀ顶éĥ¨
    -0.08
    ekar
    -0.08
    ħ§
    -0.08
    à¤Ńाव
    -0.07
    个个
    -0.07
    schuh
    -0.07
    ì°©
    -0.07
    åĪ»çĶ»
    -0.07
    POSITIVE LOGITS
    ÅĤas
    0.07
    æĹ¥æĿ¥
    0.07
    té
    0.07
     HACK
    0.06
    ãģ¾ãĤĬ
    0.06
    æıIJä¾Ľä¸Ģç§į
    0.06
    æıIJä¾Ľä¸Ģ个
    0.06
     explicitly
    0.06
     subt
    0.06
    /spec
    0.06
    Activations Density 0.003%

    No Known Activations