© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 46954
    Prev
    Next
    INDEX
    Explanations

    description of a thing

    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
    raith
    -0.09
    zá
    -0.09
     masih
    -0.09
     Plenty
    -0.08
    irs
    -0.08
     Mediterr
    -0.08
    ajor
    -0.08
    .Scheme
    -0.08
     Barcl
    -0.08
    versed
    -0.08
    POSITIVE LOGITS
     designed
    0.21
     meant
    0.17
     intended
    0.17
     located
    0.16
     that
    0.15
     aimed
    0.14
     consisting
    0.14
     created
    0.13
     composed
    0.13
     used
    0.12
    Activations Density 0.690%

    No Known Activations