© 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. 21264
    Prev
    Next
    INDEX
    Explanations

    as... the

    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
    olean
    -0.09
    ingan
    -0.09
    ----------</
    -0.07
    iert
    -0.07
    çħ§
    -0.07
    iller
    -0.07
    óln
    -0.07
    posing
    -0.07
    许åı¯
    -0.07
    æ»ĩ
    -0.07
    POSITIVE LOGITS
     prag
    0.06
    æĬķ稿éĤ®ç®±
    0.06
    äºĨä¸Ģ次
    0.06
    çĶµåŃIJéĤ®ç®±
    0.06
    æīĵåĩ»
    0.06
    ithe
    0.06
    č↵↵
    0.06
    à¹Ģà¸Ħล
    0.06
    Vir
    0.05
    (_:
    0.05
    Activations Density 0.001%

    No Known Activations