© 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. 25562
    Prev
    Next
    INDEX
    Explanations

    absence of something

    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
     versatile
    -0.08
    Vers
    -0.08
     versa
    -0.08
     Vers
    -0.07
     Matter
    -0.07
     wise
    -0.07
    REA
    -0.07
    ologically
    -0.06
     peg
    -0.06
    Misc
    -0.06
    POSITIVE LOGITS
     regard
    0.29
     regards
    0.23
     seeming
    0.18
     apparent
    0.17
     recourse
    0.17
     rhyme
    0.16
     hesitation
    0.16
     consideration
    0.15
     disregard
    0.15
     ado
    0.15
    Activations Density 0.046%

    No Known Activations