© 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. 31194
    Prev
    Next
    INDEX
    Explanations

    action phrasal verbs

    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
     leng
    -0.11
    fel
    -0.10
    yro
    -0.10
    eka
    -0.10
    892
    -0.10
    ch
    -0.10
     zeit
    -0.10
    lav
    -0.10
    mek
    -0.09
    amedi
    -0.09
    POSITIVE LOGITS
     forth
    0.15
     therein
    0.13
     down
    0.12
     away
    0.12
     out
    0.10
     up
    0.10
     aboard
    0.10
     forward
    0.09
    åĩº
    0.09
     aloud
    0.09
    Activations Density 0.514%

    No Known Activations