© 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. 14003
    Prev
    Next
    INDEX
    Explanations

    hi follow-ups

    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
    icity
    -0.11
    abeth
    -0.09
    ivery
    -0.09
     Pom
    -0.09
     Baz
    -0.09
    unic
    -0.08
    aje
    -0.08
    ober
    -0.08
    borg
    -0.08
     Ing
    -0.08
    POSITIVE LOGITS
    -tech
    0.14
    atus
    0.14
    ghest
    0.13
    -fi
    0.12
    á»ĥ
    0.12
    á»ĩn
    0.12
    ashi
    0.11
    ATUS
    0.11
    qh
    0.11
    -Speed
    0.11
    Activations Density 0.048%

    No Known Activations