© 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. 55956
    Prev
    Next
    INDEX
    Explanations

    programming element selection

    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
     Hyp
    -0.08
    gard
    -0.08
    ober
    -0.07
    /he
    -0.07
    avan
    -0.07
     BM
    -0.07
    cosa
    -0.07
    ya
    -0.07
    adj
    -0.07
     pains
    -0.07
    POSITIVE LOGITS
    uator
    0.11
    upo
    0.10
    ril
    0.10
     Consort
    0.10
     hast
    0.09
    иÑģк
    0.09
    _ns
    0.09
    ä
    0.09
    ainter
    0.09
    aison
    0.09
    Activations Density 0.001%

    No Known Activations