© 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. 51673
    Prev
    Next
    INDEX
    Explanations

    numbers and symbols followed by download or process instructions

    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
    itemap
    -0.08
    åİŁå§ĭ
    -0.07
    ç±
    -0.07
    agak
    -0.07
    çº
    -0.07
    缨
    -0.07
    áºŃy
    -0.06
    西åİ¿
    -0.06
    å½¢æĢģ
    -0.06
     syg
    -0.06
    POSITIVE LOGITS
    chten
    0.07
    Callable
    0.07
    bor
    0.07
    ikum
    0.07
     Consent
    0.06
    çIJĥåijĺ们
    0.06
    anya
    0.06
    ful
    0.06
    åħīèį£
    0.06
    以太
    0.06
    Activations Density 0.001%

    No Known Activations