© 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-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 49017
    Prev
    Next
    INDEX
    Explanations

    Names like Franco, Fran, Loren, Francois

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    bcywinski/Olmo-3-32B-Base-SAE/saes_allenai_Olmo-3-1125-32B_batch_top_k/resid_post_layer_32
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    inations
    -0.10
    nings
    -0.10
    ering
    -0.10
    --------------
    -0.10
     Sovere
    -0.09
    ---------------
    -0.09
    ±Ð¾ÑĤ
    -0.09
    nant
    -0.09
    ning
    -0.09
    sterol
    -0.09
    POSITIVE LOGITS
    ck
    0.11
    eur
    0.11
    cks
    0.10
    cken
    0.10
    icial
    0.10
    erea
    0.10
    ↵				↵
    0.10
     Kramer
    0.10
    ossip
    0.09
    EDITOR
    0.09
    Activations Density 0.013%

    No Known Activations