© 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. 16745
    Prev
    Next
    INDEX
    Explanations

    weighted averaging and mixing

    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
    itsu
    -0.08
    INET
    -0.07
    çĽ¸çŁ¥
    -0.07
    комплек
    -0.07
    uits
    -0.07
    éļħ
    -0.07
    onet
    -0.07
    onne
    -0.07
    ç¦ģæŃ¢è½¬è½½
    -0.07
    achu
    -0.07
    POSITIVE LOGITS
    blend
    0.13
     blend
    0.12
    æ··åIJĪ
    0.12
     blending
    0.12
     Blend
    0.11
    weighted
    0.11
     Mix
    0.11
     weighted
    0.11
    Blend
    0.11
     mixing
    0.11
    Activations Density 0.009%

    No Known Activations