© 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. 18201
    Prev
    Next
    INDEX
    Explanations

    biofilm formation

    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
    sequ
    -0.07
    修为
    -0.07
    deriv
    -0.07
    ionalmente
    -0.07
    unks
    -0.07
     ëĭ¤ê°Ģ
    -0.06
    åĬłæĸ¯
    -0.06
    è´µå¦ĥ
    -0.06
    alez
    -0.06
    大æīĭ
    -0.06
    POSITIVE LOGITS
    çļĦå½¢æĪIJ
    0.17
     formed
    0.16
     formation
    0.16
    çļĦ建ç«ĭ
    0.13
     oluÅŁ
    0.12
     Formation
    0.12
     terbentuk
    0.12
     íĺķìĦ±
    0.11
     formations
    0.11
     обÑĢазÑĥеÑĤÑģÑı
    0.11
    Activations Density 0.205%

    No Known Activations