© 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. 26139
    Prev
    Next
    INDEX
    Explanations

    custom motorcycles, lap steel music

    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
     anyway
    -0.08
     anyways
    -0.08
    å°ı妹
    -0.07
    ä¼¼ä¹İ
    -0.06
    agnol
    -0.06
    åijĪ
    -0.06
    æĪĸèĢħ说
    -0.06
     Anyway
    -0.06
    วาà¸Ļ
    -0.06
    åľ¨æīĢ
    -0.06
    POSITIVE LOGITS
    ä¸ŃçļĦåºĶçĶ¨
    0.12
    çī¹åĪ«æĺ¯åľ¨
    0.09
    çĶ¨å®ĥ
    0.08
     Monta
    0.08
    çŃīé¢ĨåŁŁ
    0.08
    å°¤åħ¶æĺ¯åľ¨
    0.08
     menggunakannya
    0.07
    kur
    0.07
    ivil
    0.07
     Particularly
    0.07
    Activations Density 0.190%

    No Known Activations