© 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. 51426
    Prev
    Next
    INDEX
    Explanations

    contrasting conjunctions and comparisons

    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
     terc
    -0.09
    ä¸įè¦ģ太
    -0.08
    ništ
    -0.08
    ä¸įè¦ģ让
    -0.08
    ä¹Łä¸įä¾ĭå¤ĸ
    -0.08
    åıĪä¸į失
    -0.08
    ÙĪÙĬا
    -0.07
     Ø£ÙĦا
    -0.07
    avno
    -0.07
    _hpp
    -0.07
    POSITIVE LOGITS
     whereas
    0.22
     Whereas
    0.16
     ë°ĺë©´
    0.14
     sedangkan
    0.12
     dagegen
    0.10
     mÃŃg
    0.10
     à¹ĥà¸Ļà¸Ĥà¸ĵะà¸Ĺีà¹Ī
    0.10
    åıįè§Ĥ
    0.10
     vs
    0.09
     hingegen
    0.09
    Activations Density 0.105%

    No Known Activations