© 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. 47119
    Prev
    Next
    INDEX
    Explanations

    how do you

    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
    jenigen
    -0.11
    ração
    -0.08
    ewing
    -0.08
    asure
    -0.08
     ÑĢÑıде
    -0.08
    वल
    -0.08
    reibung
    -0.08
    ecurity
    -0.08
    ÑĮÑİ
    -0.08
    è§ĤæŃ¢
    -0.08
    POSITIVE LOGITS
    er
    0.12
    i
    0.10
    o
    0.10
    nger
    0.10
     yourself
    0.09
     guys
    0.09
    zinho
    0.08
    're
    0.08
    sWith
    0.08
    и
    0.08
    Activations Density 0.281%

    No Known Activations