© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 46605
    Prev
    Next
    INDEX
    Explanations

    seeking, world, advancements, delve

    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
    åī§
    -0.07
    ouston
    -0.07
     Cheer
    -0.07
    æĽľ
    -0.07
    æŀĦæĪIJ
    -0.07
     similarly
    -0.06
    yer
    -0.06
    oshi
    -0.06
    :],
    -0.06
    astery
    -0.06
    POSITIVE LOGITS
    åĩŃåĢŁçĿĢ
    0.11
    æīįèĥ½å¤Ł
    0.10
    å°±èĥ½å¤Ł
    0.10
    éĥ½èĥ½å¤Ł
    0.10
    åŃĺåľ¨çĿĢ
    0.09
    并éĿŀæĺ¯
    0.08
    æīįèĥ½æĽ´å¥½åľ°
    0.08
    æĢĿéĩı
    0.08
    uth
    0.08
    æ¶īåıĬåĪ°
    0.08
    Activations Density 0.068%

    No Known Activations