© 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. 92271
    Prev
    Next
    INDEX
    Explanations

    junk mail

    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
    ein
    -0.12
    igo
    -0.10
    enie
    -0.09
    olle
    -0.09
    enet
    -0.09
     damned
    -0.09
    dao
    -0.09
    yne
    -0.09
    .Perform
    -0.09
    ez
    -0.08
    POSITIVE LOGITS
     bunk
    0.13
     bunker
    0.12
    pawn
    0.11
    ipop
    0.10
     beds
    0.10
    yard
    0.10
    ç®±
    0.10
     companions
    0.10
     Bedrooms
    0.10
    psc
    0.10
    Activations Density 0.010%

    No Known Activations