© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 63828
    Prev
    Next
    INDEX
    Explanations

    p-value comparisons

    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
    alde
    -0.08
    è§ĦèĮĥçļĦ
    -0.08
     normally
    -0.08
    dess
    -0.07
    çªĥ
    -0.07
    itive
    -0.07
    è¦ıç¯Ħ
    -0.07
    ient
    -0.07
    è§ĦèĮĥ
    -0.07
    normally
    -0.07
    POSITIVE LOGITS
    ëģĶ
    0.08
    ãĥ¡
    0.07
    æĭĴ
    0.07
    kens
    0.07
    çĨĻ
    0.07
    otics
    0.07
    ä½ľåģĩ
    0.07
    mén
    0.07
    LICA
    0.06
    ìľ¼
    0.06
    Activations Density 0.006%

    No Known Activations