© 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. 46349
    Prev
    Next
    INDEX
    Explanations

    cost and its effects

    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
    onis
    -0.10
     lax
    -0.10
     rich
    -0.10
    ACL
    -0.10
    ajar
    -0.10
    ighth
    -0.09
    erring
    -0.09
    /column
    -0.09
    uce
    -0.09
     Payne
    -0.09
    POSITIVE LOGITS
    -effective
    0.19
    -effect
    0.18
    lier
    0.17
    umer
    0.17
    liest
    0.16
    liness
    0.16
    umes
    0.15
     incurred
    0.14
    uming
    0.13
    umed
    0.13
    Activations Density 0.025%

    No Known Activations