© 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. 46273
    Prev
    Next
    INDEX
    Explanations

    first sequence

    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
     first
    -0.14
    _first
    -0.12
    ::-
    -0.10
    é¦ĸ
    -0.10
    kat
    -0.09
     пеÑĢв
    -0.09
    isse
    -0.09
     firstly
    -0.09
    bbe
    -0.09
    first
    -0.09
    POSITIVE LOGITS
    -hand
    0.23
    -rate
    0.23
    -ever
    0.22
    born
    0.21
    -time
    0.20
    -order
    0.19
     responders
    0.19
    .wp
    0.19
    s
    0.18
    -class
    0.18
    Activations Density 0.191%

    No Known Activations