© 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. 3681
    Prev
    Next
    INDEX
    Explanations

    suspecting that

    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
    ocker
    -0.10
    ensing
    -0.09
    ening
    -0.09
    eker
    -0.09
    ora
    -0.09
    away
    -0.08
    worm
    -0.08
    plode
    -0.08
     slick
    -0.08
    mx
    -0.08
    POSITIVE LOGITS
     foul
    0.16
    ively
    0.13
    /question
    0.12
     strongly
    0.12
    mention
    0.11
     Garland
    0.10
    pcion
    0.10
    rious
    0.10
     Huff
    0.10
    ibility
    0.10
    Activations Density 0.025%

    No Known Activations