© 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. 3358
    Prev
    Next
    INDEX
    Explanations

    comparing actions to

    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
    URLException
    -0.08
    Vectorizer
    -0.07
    zana
    -0.07
    gua
    -0.07
    ranti
    -0.07
    figcaption
    -0.07
    Č↵
    -0.07
    intervista
    -0.07
     eased
    -0.07
    [--
    -0.07
    POSITIVE LOGITS
     cioè
    0.08
     ÑıкобÑĭ
    0.07
     appunto
    0.07
    ed
    0.07
    oper
    0.06
    isc
    0.06
    åºĶå½ĵä¾Ŀçħ§
    0.06
    icon
    0.06
     und
    0.06
    .vm
    0.06
    Activations Density 0.746%

    No Known Activations