© 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. 50622
    Prev
    Next
    INDEX
    Explanations

    strings enclosed in quotes

    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
     outs
    -0.08
    'A
    -0.08
    ÌĢ
    -0.07
    neh
    -0.07
     neh
    -0.07
    #@
    -0.07
    atab
    -0.06
     convo
    -0.06
     outing
    -0.06
    .@
    -0.06
    POSITIVE LOGITS
     buz
    0.12
    asz
    0.11
    anium
    0.11
    Matching
    0.10
    gent
    0.10
     misc
    0.10
     Related
    0.10
     unp
    0.10
     hÃłng
    0.10
     Slee
    0.10
    Activations Density 0.003%

    No Known Activations