© 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. 113652
    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
    alia
    -0.14
    rie
    -0.13
     Mour
    -0.10
     Birch
    -0.10
     Colleg
    -0.10
     Ez
    -0.10
     Ston
    -0.10
    alam
    -0.10
     Rag
    -0.10
    resher
    -0.10
    POSITIVE LOGITS
    ying
    0.10
    çĿ
    0.09
    ied
    0.08
     Lem
    0.08
     Lump
    0.08
     continuously
    0.08
    riot
    0.08
    ongs
    0.08
    yi
    0.08
     relentlessly
    0.08
    Activations Density 0.274%

    No Known Activations