© 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. 64447
    Prev
    Next
    INDEX
    Explanations

    sporulation, molt, regression, hibern, decidual, surge, differentiation, breakdown

    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
    اصر
    -0.08
     AUTOR
    -0.08
    Ñīе
    -0.08
    éĽ¨éľ²
    -0.07
    èļĬåŃIJ
    -0.07
    (patch
    -0.07
    à¹Īวย
    -0.07
    ç¦Ħ
    -0.07
     visibilité
    -0.07
    å·¥ä½ľå¼Ģå±ķ
    -0.07
    POSITIVE LOGITS
     preparation
    0.11
    åĩĨå¤ĩ
    0.11
     prepares
    0.10
     ì¤Ģë¹Ħ
    0.10
     prepar
    0.10
     readiness
    0.09
     preparations
    0.09
     prepare
    0.09
     preparing
    0.09
     Preparation
    0.09
    Activations Density 0.136%

    No Known Activations