© 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. 18167
    Prev
    Next
    INDEX
    Explanations

    yes/no questions

    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
     chop
    -0.10
     Cuban
    -0.10
     cauliflower
    -0.09
    ael
    -0.09
     Nap
    -0.09
    lock
    -0.09
    åİ
    -0.09
    .clip
    -0.09
    illac
    -0.09
     specializing
    -0.09
    POSITIVE LOGITS
     yes
    0.10
    Vote
    0.10
     aver
    0.10
     Share
    0.09
     Tell
    0.09
    ken
    0.09
     Vote
    0.09
     Brun
    0.09
     thor
    0.09
     thumbs
    0.09
    Activations Density 0.011%

    No Known Activations