© 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. 798
    Prev
    Next
    INDEX
    Explanations

    setters, put, reset, methods

    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
     Holl
    -0.08
     Conc
    -0.08
     Purchase
    -0.08
    seed
    -0.08
    cla
    -0.08
     Ec
    -0.08
    nid
    -0.07
    /mit
    -0.07
     doInBackground
    -0.07
    zi
    -0.07
    POSITIVE LOGITS
    /reset
    0.13
    bef
    0.11
    /remove
    0.11
    /update
    0.11
    imax
    0.10
    IfNeeded
    0.10
     Done
    0.10
    OrUpdate
    0.10
     bef
    0.09
     done
    0.09
    Activations Density 1.415%

    No Known Activations