© 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. 33839
    Prev
    Next
    INDEX
    Explanations

    aw + words ending in 'ski', 'den', 'arr', 'azu', 'atch', 'ae', 'o', 'ra', 'la', 'A'

    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
    a
    -0.14
    i
    -0.11
    aar
    -0.10
    apor
    -0.10
    y
    -0.10
    elper
    -0.09
    nect
    -0.09
     Seas
    -0.09
    cales
    -0.09
    chart
    -0.08
    POSITIVE LOGITS
    fully
    0.16
    á»įn
    0.13
    akening
    0.13
    ski
    0.12
    ful
    0.11
    akens
    0.11
    icontrol
    0.11
    yer
    0.10
    asaki
    0.10
    akeFromNib
    0.10
    Activations Density 0.042%

    No Known Activations