© 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. 4178
    Prev
    Next
    INDEX
    Explanations

    estimate, determine, calculate, find

    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
    /
    -0.06
    XXXX
    -0.06
     no
    -0.05
     i
    -0.05
     +
    -0.05
     &
    -0.05
    XXX
    -0.05
    etten
    -0.05
    ess
    -0.05
    (
    -0.05
    POSITIVE LOGITS
    æĢ»çļĦ
    0.11
    端åĢª
    0.10
    [:]
    0.10
    óta
    0.09
     IMPLIED
    0.09
    needed
    0.09
    æŃ¤æ¥¼
    0.09
     Needed
    0.09
    ispens
    0.08
    abler
    0.08
    Activations Density 0.015%

    No Known Activations