© 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. 28987
    Prev
    Next
    INDEX
    Explanations

    separating items or lists

    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
    zs
    -0.06
    çĶŁäº§ä¸Ń
    -0.06
    O
    -0.06
    ens
    -0.06
    unut
    -0.06
    ually
    -0.06
    .um
    -0.06
    iful
    -0.06
    .atom
    -0.06
    elman
    -0.06
    POSITIVE LOGITS
     spiagg
    0.08
    å°Ķåħĭ
    0.08
    illeur
    0.08
    egro
    0.08
    traits
    0.08
    æµ®çĶŁ
    0.08
    akeup
    0.07
    лоÑģо
    0.07
    alus
    0.07
    éroport
    0.07
    Activations Density 0.039%

    No Known Activations