© 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. 31926
    Prev
    Next
    INDEX
    Explanations

    eigenvalues and eigenvectors

    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
    prise
    -0.08
    ledged
    -0.08
    ighted
    -0.08
    à§įড
    -0.08
    aner
    -0.08
    æĻ¦
    -0.07
    ÅĽÄĩ
    -0.07
    <|box_end|>
    -0.07
    ipper
    -0.07
    çĥ¨
    -0.07
    POSITIVE LOGITS
    ree
    0.10
    ler
    0.09
    rist
    0.08
    els
    0.08
    ilia
    0.07
    reek
    0.07
    åĽ½éĻħæľºåľº
    0.07
    geno
    0.07
    liest
    0.07
    ris
    0.07
    Activations Density 0.001%

    No Known Activations