© 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. 58543
    Prev
    Next
    INDEX
    Explanations

    implied warranty or 0

    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
    etty
    -0.09
     envol
    -0.08
    ãĤ¯ãĤ¿
    -0.08
    εÏģι
    -0.08
    rof
    -0.07
    ÙĦÙĤ
    -0.07
    ovens
    -0.07
    oined
    -0.07
    ÙĥÙĪر
    -0.07
    ấy
    -0.07
    POSITIVE LOGITS
    ensa
    0.07
    ense
    0.06
    eb
    0.06
    éłĵ
    0.06
    çĪ¾
    0.06
    deps
    0.06
    ed
    0.06
    ue
    0.06
    dep
    0.06
    ards
    0.06
    Activations Density 0.116%

    No Known Activations