© 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. 19060
    Prev
    Next
    INDEX
    Explanations

    If

    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
    erso
    -0.08
    eland
    -0.08
    går
    -0.08
    ãĥĥãĤ«ãĥ¼
    -0.08
     Yar
    -0.07
    ermen
    -0.07
    åĦ¿
    -0.07
    åĽłæŃ¤åľ¨
    -0.07
    еÑħ
    -0.07
    oger
    -0.07
    POSITIVE LOGITS
    propri
    0.07
    讨
    0.07
    ous
    0.06
    dup
    0.06
    翼翼
    0.06
    daw
    0.06
     paso
    0.06
    dj
    0.06
    forth
    0.06
    ito
    0.06
    Activations Density 0.012%

    No Known Activations