© 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. 24962
    Prev
    Next
    INDEX
    Explanations

    ask questions or for information

    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
    idor
    -0.10
    blind
    -0.10
    agra
    -0.10
     instruct
    -0.10
     tract
    -0.10
     listener
    -0.10
     help
    -0.10
     willingly
    -0.09
     Answer
    -0.09
     blindly
    -0.09
    POSITIVE LOGITS
     references
    0.11
     resend
    0.10
    /send
    0.10
     stip
    0.10
    /security
    0.09
    -out
    0.09
    /display
    0.09
     past
    0.09
     evid
    0.09
     screenshots
    0.09
    Activations Density 0.009%

    No Known Activations