© 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. 3382
    Prev
    Next
    INDEX
    Explanations

    adjective suffix -less

    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
    ish
    -0.11
    ick
    -0.11
    ical
    -0.10
    rim
    -0.10
    er
    -0.10
    ative
    -0.10
    ry
    -0.10
    ity
    -0.10
    ied
    -0.10
    atory
    -0.09
    POSITIVE LOGITS
    nes
    0.17
    /un
    0.11
     VOID
    0.11
     wonders
    0.11
    NESS
    0.11
    kaar
    0.11
     void
    0.10
    phem
    0.10
     wonder
    0.10
    lich
    0.09
    Activations Density 0.058%

    No Known Activations