© 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. 117258
    Prev
    Next
    INDEX
    Explanations

    v followed by specific words

    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
    uts
    -0.10
    attr
    -0.08
    lias
    -0.08
     consolid
    -0.08
    ugg
    -0.08
     misd
    -0.07
    akest
    -0.07
    ione
    -0.07
     Instit
    -0.07
     Bol
    -0.07
    POSITIVE LOGITS
     vouchers
    0.17
     vagina
    0.16
     voucher
    0.16
     voting
    0.15
     Voting
    0.15
     vacation
    0.15
     vocabulary
    0.14
    antage
    0.14
     vomiting
    0.14
     vacancy
    0.14
    Activations Density 0.196%

    No Known Activations