© 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. 88271
    Prev
    Next
    INDEX
    Explanations

    reco / recom

    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
    uters
    -0.09
    oppers
    -0.09
     sm
    -0.09
     Downs
    -0.09
     bursting
    -0.09
    lich
    -0.08
     boldly
    -0.08
    yat
    -0.08
     TRI
    -0.08
    ously
    -0.08
    POSITIVE LOGITS
     rec
    0.23
     Rec
    0.20
    rec
    0.19
    /rec
    0.19
    Rec
    0.18
    -rec
    0.16
    (rec
    0.16
     REC
    0.14
    _rec
    0.14
    .rec
    0.14
    Activations Density 0.073%

    No Known Activations