© 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. 116808
    Prev
    Next
    INDEX
    Explanations

    relation to later or earlier

    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
    con
    -0.09
    ny
    -0.09
     sooner
    -0.09
     bisher
    -0.09
    assic
    -0.09
     ABOVE
    -0.09
     Parsons
    -0.09
     commencement
    -0.09
     Fern
    -0.09
    ahir
    -0.09
    POSITIVE LOGITS
    aday
    0.10
    roe
    0.09
    argo
    0.09
    day
    0.08
     afternoon
    0.08
    reserved
    0.08
    ffe
    0.08
     day
    0.08
    weg
    0.08
    -day
    0.08
    Activations Density 0.032%

    No Known Activations