© 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. 15007
    Prev
    Next
    INDEX
    Explanations

    prepares to, before the

    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
    Front
    -0.07
    -front
    -0.07
    æľīæīĢ
    -0.07
    uffers
    -0.06
     NOT
    -0.06
    åģļçļĦå°±æĺ¯
    -0.06
    ек
    -0.06
    _parms
    -0.06
    !!!
    -0.06
    çıĤ
    -0.06
    POSITIVE LOGITS
    åĽŀåIJĪ
    0.08
    è§
    0.08
    交çĶµ
    0.07
    ever
    0.07
    Ñıн
    0.07
     finalement
    0.07
    orsa
    0.07
    ysel
    0.07
    tas
    0.07
    ÙĤÙĬÙĤØ©
    0.07
    Activations Density 1.424%

    No Known Activations