© 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. 39681
    Prev
    Next
    INDEX
    Explanations

    code blocks with `()` or `init`

    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
    渣
    -0.06
    ens
    -0.06
    ains
    -0.06
    å¾Ĺä¸į
    -0.06
    isson
    -0.06
    é±¼
    -0.06
    ain
    -0.06
    |
    -0.06
    -collection
    -0.06
    èĩªå·±ä¸į
    -0.06
    POSITIVE LOGITS
    arkan
    0.08
    ``,
    0.07
    plos
    0.07
    IRO
    0.07
    Proc
    0.07
    anaan
    0.07
    obili
    0.07
    è¸Ĭ
    0.07
    以德
    0.07
    Indented
    0.07
    Activations Density 0.081%

    No Known Activations