© 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. 964
    Prev
    Next
    INDEX
    Explanations

    indirectly, ultimately

    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
    å²ļ
    -0.07
    agh
    -0.07
     Partnership
    -0.06
     rach
    -0.06
    anni
    -0.06
     cin
    -0.06
    èĬ³èįī
    -0.06
    _acl
    -0.06
    roma
    -0.06
    éĽ
    -0.06
    POSITIVE LOGITS
    éĹ´æİ¥
    0.15
     indirectly
    0.15
     ultimately
    0.14
     indire
    0.14
     indirect
    0.13
    æľĢç»Ī
    0.13
    æľĢç»Īè¿ĺæĺ¯
    0.12
    缴æİ¥ä¸İ
    0.12
     ultimate
    0.12
     Ultimately
    0.12
    Activations Density 0.221%

    No Known Activations