© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 113646
    Prev
    Next
    INDEX
    Explanations

    comparisons using than

    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
     Already
    -0.09
     unos
    -0.09
    ãģĻ
    -0.09
    usic
    -0.09
    already
    -0.09
    rier
    -0.09
    [ID
    -0.09
     sharper
    -0.09
    çļ
    -0.09
    exus
    -0.09
    POSITIVE LOGITS
     usual
    0.15
     typical
    0.15
     necessary
    0.14
     warranted
    0.14
     desirable
    0.14
     advisable
    0.13
     ideally
    0.13
     average
    0.13
     any
    0.13
     ideal
    0.13
    Activations Density 0.048%

    No Known Activations