© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1025-7B
    5. 16-RES-MATRYOSHKA-65K
    7. 56263
    Prev
    Next
    INDEX
    Explanations

    by javadoc

    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
    unt
    -0.08
     key
    -0.08
     sci
    -0.08
     focal
    -0.08
    /sc
    -0.08
     Roc
    -0.07
     materially
    -0.07
     rer
    -0.07
    ains
    -0.07
     Harvard
    -0.07
    POSITIVE LOGITS
    achs
    0.12
     stil
    0.10
     Raised
    0.10
     skirts
    0.09
    веÑĤ
    0.09
    hores
    0.09
     Resorts
    0.09
    dde
    0.09
     Swinger
    0.09
    Wars
    0.09
    Activations Density 0.005%

    No Known Activations