© 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. 27453
    Prev
    Next
    INDEX
    Explanations

    numbers followed by parenthesis or "offers"

    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
    -
    -0.07
    od
    -0.07
    ife
    -0.06
    ik
    -0.06
    -b
    -0.06
    oll
    -0.06
    æĤį
    -0.06
    -t
    -0.06
    ostas
    -0.06
    ost
    -0.06
    POSITIVE LOGITS
    udir
    0.08
    ãĥĨãĥĬ
    0.08
    ụa
    0.08
    ాయ
    0.08
    resents
    0.08
    еÑĢбÑĥ
    0.08
    以åĮĹ
    0.08
    ä½ĵèĤ²ä¸Ńå¿ĥ
    0.08
    unar
    0.07
    çī©è³ĩ
    0.07
    Activations Density 0.002%

    No Known Activations