© 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. 60362
    Prev
    Next
    INDEX
    Explanations

    rules configurations

    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
    enis
    -0.08
    éĩįäºİ
    -0.08
    彬
    -0.08
    ersp
    -0.08
    对æīĢ
    -0.07
    ouz
    -0.07
    ÑĤÑĤ
    -0.07
    undan
    -0.07
     departamento
    -0.07
    imah
    -0.07
    POSITIVE LOGITS
     otherwise
    0.12
    åİŁæľī
    0.12
    åİŁæľīçļĦ
    0.11
    otherwise
    0.10
    å·²æľīçļĦ
    0.09
     altrimenti
    0.09
     already
    0.09
    å·²ç»ıå¾Ī
    0.08
    existing
    0.08
     existing
    0.08
    Activations Density 0.249%

    No Known Activations