© 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. 42800
    Prev
    Next
    INDEX
    Explanations

    projection onto

    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
     frit
    -0.08
    uku
    -0.07
    åıĺåĮĸçļĦ
    -0.07
    åIJĦåĽ½
    -0.07
     Jok
    -0.07
    ondern
    -0.07
     hardly
    -0.07
    åĽ½éĻħ
    -0.06
    åIJĦåĽ½çļĦ
    -0.06
     Register
    -0.06
    POSITIVE LOGITS
     onto
    0.10
    nger
    0.08
    iors
    0.07
    Alg
    0.07
    antor
    0.07
    .dense
    0.07
    æ±Ĥ羣
    0.07
    onto
    0.07
    ivals
    0.07
     orthogonal
    0.07
    Activations Density 0.005%

    No Known Activations