© 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. 30318
    Prev
    Next
    INDEX
    Explanations

    tube amp

    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
    heber
    -0.09
    åİ»æĥ³
    -0.08
    浪
    -0.08
    èµĦ
    -0.08
    ination
    -0.08
    енÑĤаÑĨиÑı
    -0.08
    =set
    -0.08
    ÕŃ
    -0.07
    ÎŃν
    -0.07
    elib
    -0.07
    POSITIVE LOGITS
    Âł
    0.06
    å³
    0.06
    ErrorResponse
    0.06
    éĶĢåĶ®é¢Ŀ
    0.06
    .cms
    0.06
     Kod
    0.06
     Adelaide
    0.06
    otr
    0.06
    .ot
    0.05
    ï
    0.05
    Activations Density 1.722%

    No Known Activations