© 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. 112514
    Prev
    Next
    INDEX
    Explanations

    have to followed by a verb

    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
     amid
    -0.10
     pus
    -0.10
     jab
    -0.09
    osti
    -0.09
     Perr
    -0.08
    OST
    -0.08
     Lawson
    -0.08
    antro
    -0.08
     Reid
    -0.08
    151
    -0.08
    POSITIVE LOGITS
     wait
    0.17
    wait
    0.16
     REALLY
    0.15
     hurry
    0.14
     tread
    0.12
     waits
    0.12
    ovo
    0.12
     careful
    0.11
     awaits
    0.11
     ajust
    0.11
    Activations Density 0.035%

    No Known Activations