© 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. 19789
    Prev
    Next
    INDEX
    Explanations

    as of / as with / as a

    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
    icolore
    -0.08
    eeper
    -0.07
    kreis
    -0.07
    stration
    -0.07
    ÏĦαι
    -0.07
    lessly
    -0.07
    mploy
    -0.07
    ondern
    -0.07
    itsu
    -0.07
    aveur
    -0.06
    POSITIVE LOGITS
    ahi
    0.11
    pects
    0.10
    aad
    0.09
    semble
    0.09
    piring
    0.09
    igur
    0.08
    paragus
    0.08
    adi
    0.08
    ani
    0.08
    alin
    0.08
    Activations Density 0.091%

    No Known Activations