© 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. 48644
    Prev
    Next
    INDEX
    Explanations

    epsilon and delta

    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
    νοÏį
    -0.09
     tutt
    -0.09
    yty
    -0.08
    .pan
    -0.08
    ìĨĶ
    -0.08
    ContentLoaded
    -0.08
    yman
    -0.08
    ãĤ¦ãĥĪ
    -0.08
    ĽĦ
    -0.07
    jadi
    -0.07
    POSITIVE LOGITS
    ingly
    0.06
    -runtime
    0.06
    å»ī
    0.06
    stream
    0.06
     cant
    0.06
    论è¯Ń
    0.06
     Margin
    0.06
     margin
    0.06
    亲
    0.06
    atively
    0.06
    Activations Density 0.003%

    No Known Activations