© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 87886
    Prev
    Next
    INDEX
    Explanations

    numbers and titles

    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
    Negative Logits
    /of
    -0.13
    /if
    -0.13
     bli
    -0.13
    /OR
    -0.12
     Fauc
    -0.12
     Swal
    -0.12
     dela
    -0.12
     Craw
    -0.12
    IFn
    -0.12
     Amount
    -0.11
    POSITIVE LOGITS
    <|endoftext|>
    0.09
    ”—
    0.06
    --------------------------------
    0.06
    GLOSS
    0.06
     bluff
    0.06
     stere
    0.06
     misleading
    0.06
     rush
    0.05
     finger
    0.05
     gal
    0.05
    Activations Density 0.083%

    No Known Activations