© 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. 25808
    Prev
    Next
    INDEX
    Explanations

    individual

    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
    nikov
    -0.08
    UGE
    -0.08
    ä¸Ģç·Ĵ
    -0.08
    Ñħоз
    -0.07
    åIJİç½®
    -0.07
     Muda
    -0.07
    éĩijæĸ¯
    -0.07
    VRT
    -0.07
    ä¸Ģæķ°
    -0.07
    ä¸Ń人
    -0.07
    POSITIVE LOGITS
     individual
    0.24
     individually
    0.23
    个ä½ĵ
    0.22
    individual
    0.21
     Individual
    0.21
    individ
    0.21
     individuale
    0.21
    个ä½ĵçļĦ
    0.20
     individuales
    0.20
    Individual
    0.20
    Activations Density 0.152%

    No Known Activations