© 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. 18654
    Prev
    Next
    INDEX
    Explanations

    normalizing or normal state

    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
    tlement
    -0.11
    jenigen
    -0.09
    ë©į
    -0.09
    anela
    -0.09
    aminer
    -0.08
    psilon
    -0.08
    ffer
    -0.08
    kel
    -0.08
    ivism
    -0.08
    ivist
    -0.08
    POSITIVE LOGITS
    cy
    0.12
    erweise
    0.11
    ised
    0.11
    ity
    0.11
    izing
    0.11
    ly
    0.10
    isation
    0.10
    izations
    0.09
    issimo
    0.09
    -ish
    0.09
    Activations Density 0.031%

    No Known Activations