© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 44178
    Prev
    Next
    INDEX
    Explanations

    parameter or return value descriptions

    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
    fare
    -0.08
    åij½çļĦ
    -0.07
    ”—
    -0.07
    kien
    -0.07
     separately
    -0.07
    äd
    -0.06
    imers
    -0.06
     separate
    -0.06
    çŃīåħ¶ä»ĸ
    -0.06
     Gorgeous
    -0.06
    POSITIVE LOGITS
     {@
    0.08
    {@
    0.08
    @param
    0.08
    ÙĨØ©
    0.08
    erede
    0.07
     Tac
    0.07
    æĹłåīį
    0.07
    bpp
    0.06
    ",__
    0.06
    èĻij
    0.06
    Activations Density 0.040%

    No Known Activations