© 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. 14273
    Prev
    Next
    INDEX
    Explanations

    verbs followed by prepositions

    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
    imm
    -0.10
     NH
    -0.09
     however
    -0.09
    SD
    -0.08
     Sus
    -0.08
    edd
    -0.08
    .—
    -0.08
    _HTML
    -0.08
     tela
    -0.08
     ì²ĺ
    -0.08
    POSITIVE LOGITS
    printStats
    0.10
    iew
    0.09
    @dynamic
    0.09
    /lic
    0.09
    rebbe
    0.08
    herits
    0.08
    -caret
    0.08
    GetEnumerator
    0.08
    -sama
    0.08
    -has
    0.08
    Activations Density 1.200%

    No Known Activations