© 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. 8645
    Prev
    Next
    INDEX
    Explanations

    understanding personal experiences

    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
    iget
    -0.09
    -feed
    -0.09
    inales
    -0.08
    agian
    -0.08
    è¦ģåĬłå¤§
    -0.08
    对æĪij们çļĦ
    -0.08
    Compat
    -0.08
    éos
    -0.08
    sker
    -0.08
     Gober
    -0.08
    POSITIVE LOGITS
    æĦŁåIJĮ
    0.15
    亲身ç»ıåİĨ
    0.10
    亲身ä½ĵéªĮ
    0.10
     similar
    0.10
    æ·±åĪ»çIJĨ解
    0.10
     experience
    0.09
     experienced
    0.09
     empathy
    0.09
    ç»ıåİĨè¿ĩ
    0.09
    çĽ¸ä¼¼
    0.09
    Activations Density 0.217%

    No Known Activations