© 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. 18840
    Prev
    Next
    INDEX
    Explanations

    enabling or disabling features

    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
    unami
    -0.09
     demás
    -0.08
    enticate
    -0.08
    णि
    -0.08
    weet
    -0.07
    elper
    -0.07
    gether
    -0.07
    éģĹçĹĩ
    -0.07
    itical
    -0.07
     мимо
    -0.07
    POSITIVE LOGITS
    /disable
    0.21
    /dis
    0.10
    ment
    0.10
    anced
    0.08
    leanor
    0.08
    forth
    0.08
     terjadinya
    0.08
    avour
    0.07
    ancement
    0.07
    äºĨä¸Ģåľº
    0.07
    Activations Density 0.035%

    No Known Activations