© 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. 8162
    Prev
    Next
    INDEX
    Explanations

    quoted strings

    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
    èĩªå·±
    -0.09
    ings
    -0.08
    Ñĥ
    -0.08
    .nlm
    -0.07
    ãĤĪãģĨãģ«
    -0.07
    ãģĺãĤģãģ¦
    -0.06
    Ø®
    -0.06
    µ
    -0.06
    ftware
    -0.06
    aneous
    -0.06
    POSITIVE LOGITS
    ses
    0.11
    Ùħ
    0.10
    iola
    0.10
    aup
    0.10
    sb
    0.10
     latter
    0.10
    zinho
    0.10
    eration
    0.09
    yth
    0.09
    alet
    0.09
    Activations Density 0.269%

    No Known Activations