© 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. 18533
    Prev
    Next
    INDEX
    Explanations

    Published, luck, specifying

    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
    Gratis
    -0.12
    .actual
    -0.11
    Porno
    -0.10
    Https
    -0.10
    Scala
    -0.10
    Bitte
    -0.09
    Postal
    -0.09
     sublic
    -0.09
    <article
    -0.09
    unately
    -0.09
    POSITIVE LOGITS
    ,eg
    0.07
    @stop
    0.07
     IMG
    0.07
     firstly
    0.07
    cé
    0.07
    ,ev
    0.06
    a
    0.06
    AndUpdate
    0.06
     ``
    0.06
     sluggish
    0.06
    Activations Density 1.776%

    No Known Activations