© 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. 33660
    Prev
    Next
    INDEX
    Explanations

    graded rings and differential forms

    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
    æĬī
    -0.07
    çĽ¹
    -0.07
    å¿ĥåºķ
    -0.07
    ÖĦ
    -0.07
    é«ĺç´łè´¨
    -0.07
    /thumb
    -0.07
     Pare
    -0.07
    каз
    -0.06
    æĭĩ
    -0.06
    _thumb
    -0.06
    POSITIVE LOGITS
     Hors
    0.08
    ropri
    0.08
    éĩįéĺ³
    0.08
    ikel
    0.07
    éļİ
    0.07
    ifest
    0.07
     неком
    0.07
    å¥ĩ
    0.07
    è´Ł
    0.07
    _offsets
    0.07
    Activations Density 0.006%

    No Known Activations