© 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. 46972
    Prev
    Next
    INDEX
    Explanations

    drag and drop

    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
    aille
    -0.10
    ille
    -0.10
    iler
    -0.09
    erras
    -0.09
     inher
    -0.09
     ks
    -0.08
    anonymous
    -0.08
     weakest
    -0.08
     statistical
    -0.08
     mat
    -0.08
    POSITIVE LOGITS
     Sext
    0.11
    .realm
    0.10
    lector
    0.10
     Destination
    0.10
    (and
    0.09
    uther
    0.09
     floated
    0.09
     unsuccessfully
    0.08
     Countdown
    0.08
     Sher
    0.08
    Activations Density 0.005%

    No Known Activations