© 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. 29624
    Prev
    Next
    INDEX
    Explanations

    browser names after "and"

    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
     chairs
    -0.20
     championships
    -0.18
     chair
    -0.17
     chemotherapy
    -0.17
     Chairs
    -0.17
     cholesterol
    -0.16
     Chile
    -0.16
     Chelsea
    -0.16
     Ñĩ
    -0.16
     championship
    -0.16
    POSITIVE LOGITS
    обÑĭ
    0.11
    ripe
    0.10
    @section
    0.09
     Hubb
    0.09
    sty
    0.09
     Soda
    0.09
    CALE
    0.09
    CPF
    0.09
    sono
    0.09
    ator
    0.08
    Activations Density 0.807%

    No Known Activations