© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1025-7B
    5. 16-RES-MATRYOSHKA-65K
    7. 61458
    Prev
    Next
    INDEX
    Explanations

    ge followed by q

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    decoderesearch/olmo-3-saes/olmo-3-1025-7b
    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
    y
    -0.13
    inning
    -0.11
    ing
    -0.10
    scalar
    -0.09
    yb
    -0.08
    yd
    -0.07
    able
    -0.07
    ement
    -0.07
    e
    -0.07
    snap
    -0.07
    POSITIVE LOGITS
    amp
    0.10
    nde
    0.10
     prospect
    0.09
    ussen
    0.09
    q
    0.09
    اب
    0.09
    lov
    0.08
    obook
    0.08
    .!
    0.08
    ÐĤ
    0.08
    Activations Density 0.004%

    No Known Activations