© 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. Olmo-3-1025-7B
    5. 16-RES-MATRYOSHKA-65K
    7. 57347
    Prev
    Next
    INDEX
    Explanations

    second phase

    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
    world
    -0.10
    owie
    -0.09
    ugs
    -0.09
    iances
    -0.09
    deg
    -0.08
    aza
    -0.08
     insan
    -0.08
    COPY
    -0.08
    ROC
    -0.08
    iat
    -0.08
    POSITIVE LOGITS
     ren
    0.09
     Sle
    0.08
    inactive
    0.08
    orte
    0.08
    oret
    0.07
    )))),
    0.07
     Fired
    0.07
    ly
    0.07
    Bounding
    0.07
     hearing
    0.07
    Activations Density 0.018%

    No Known Activations