© 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. 29576
    Prev
    Next
    INDEX
    Explanations

    consequence and explanation introducers

    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
    è¯Ĺæĸĩ
    -0.07
    regar
    -0.07
    ç¤
    -0.07
    ancel
    -0.07
     biri
    -0.07
    é¾Ļåĩ¤
    -0.07
     бÑĭваеÑĤ
    -0.07
     éppen
    -0.07
    å²Ĺ
    -0.07
    antan
    -0.07
    POSITIVE LOGITS
    æľīå¦Ĥ
    0.09
    encion
    0.08
     straightforward
    0.07
    nern
    0.07
    åħ³éĶ®çļĦ
    0.07
    åħ³éĶ®åľ¨äºİ
    0.07
    ×Ļ×Ļ×Ŀ
    0.06
    :
    0.06
    huis
    0.06
    äºķçĦ¶
    0.06
    Activations Density 0.001%

    No Known Activations