© 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. 42720
    Prev
    Next
    INDEX
    Explanations

    document structure metadata

    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
    çĶļèĩ³
    -0.07
    uy
    -0.07
    ries
    -0.07
    imina
    -0.07
    RIES
    -0.07
    ima
    -0.07
    åĩĮ空
    -0.06
    imas
    -0.06
    çŁ¢å¿Ĺ
    -0.06
    çŁ¾
    -0.06
    POSITIVE LOGITS
    æİĺéĩij
    0.07
    ason
    0.07
    pard
    0.07
    dens
    0.07
    è¿Ķ
    0.07
    ãĥĭãĥ³ãĤ°
    0.07
    é«ĺå¯Ĩ
    0.07
    Ùİار
    0.07
    itra
    0.07
    cich
    0.07
    Activations Density 0.004%

    No Known Activations