© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 91902
    Prev
    Next
    INDEX
    Explanations

    des- at the start of words

    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
    uien
    -0.10
    eel
    -0.10
     Packing
    -0.10
    cies
    -0.10
    zie
    -0.10
    ture
    -0.09
    cil
    -0.09
     Powered
    -0.09
     solic
    -0.09
    allon
    -0.09
    POSITIVE LOGITS
     Moines
    0.14
    cribed
    0.12
    icc
    0.12
    conto
    0.11
    patch
    0.11
    picable
    0.11
    cribing
    0.10
    pres
    0.10
    criptive
    0.10
    pot
    0.10
    Activations Density 0.056%

    No Known Activations