© 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. 29458
    Prev
    Next
    INDEX
    Explanations

    votes in favour

    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
     someone
    -0.18
     полÑĮзоваÑĤелÑı
    -0.17
     humans
    -0.16
     persons
    -0.16
     somebody
    -0.16
     individuals
    -0.15
     fellow
    -0.15
     people
    -0.15
     him
    -0.14
     whoever
    -0.14
    POSITIVE LOGITS
    enia
    0.11
    ogg
    0.10
    emente
    0.10
     Throne
    0.09
    uger
    0.09
     receipt
    0.09
     abortions
    0.09
    ERE
    0.09
     pregnancies
    0.09
    à¸ģาร
    0.09
    Activations Density 3.050%

    No Known Activations