© 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. 64284
    Prev
    Next
    INDEX
    Explanations

    quotes and punctuation

    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
     Dek
    -0.08
     *_
    -0.07
     Pais
    -0.07
    大åIJį
    -0.07
     ord
    -0.07
    ãĥ¼ãĥĦ
    -0.06
    订
    -0.06
    vince
    -0.06
    åĪĨéħį
    -0.06
    ORD
    -0.06
    POSITIVE LOGITS
    วย
    0.08
    缸åħ³éĹ®çŃĶ
    0.08
    ado
    0.07
    å¹³æĪIJ
    0.07
    chini
    0.07
    adou
    0.07
    åĪ«æıIJ
    0.07
    upal
    0.07
     wobei
    0.07
    _mysql
    0.07
    Activations Density 0.022%

    No Known Activations