© 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. 92267
    Prev
    Next
    INDEX
    Explanations

    .00 or .99 endings

    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
    wed
    -0.09
     Printable
    -0.09
    apia
    -0.09
    igi
    -0.09
     honeymoon
    -0.08
     Bride
    -0.08
     sine
    -0.08
     Milton
    -0.08
     recip
    -0.08
    ieu
    -0.08
    POSITIVE LOGITS
    95
    0.13
    99
    0.10
     pars
    0.10
    obra
    0.10
    995
    0.09
    halt
    0.09
     Klein
    0.09
    iesen
    0.09
     sens
    0.09
     Dien
    0.09
    Activations Density 0.032%

    No Known Activations