© 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. 92262
    Prev
    Next
    INDEX
    Explanations

    mad followed by 'an' or 'is' or 'oc'

    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
    abe
    -0.09
    able
    -0.09
    aar
    -0.09
     corpor
    -0.08
     Honor
    -0.08
    ably
    -0.08
    ont
    -0.08
    orre
    -0.08
     duro
    -0.08
    site
    -0.08
    POSITIVE LOGITS
     ABOUT
    0.12
    libs
    0.11
     About
    0.11
    enci
    0.11
    hub
    0.11
    hya
    0.10
     Madd
    0.10
    RP
    0.10
    deaux
    0.10
     undone
    0.10
    Activations Density 0.007%

    No Known Activations