© 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. 56404
    Prev
    Next
    INDEX
    Explanations

    lesions

    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
    orial
    -0.11
    -0.11
     Swe
    -0.09
    icut
    -0.08
    encias
    -0.08
    à¸ļ
    -0.08
    asa
    -0.08
    riel
    -0.08
    aland
    -0.08
    lining
    -0.07
    POSITIVE LOGITS
    y
    0.11
    ocos
    0.10
    er
    0.10
    EEP
    0.10
    ate
    0.09
    erie
    0.09
    lv
    0.09
    اء
    0.09
    .object
    0.09
    ocker
    0.09
    Activations Density 0.009%

    No Known Activations