© 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. 46642
    Prev
    Next
    INDEX
    Explanations

    frame numbers

    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
    indi
    -0.08
    amil
    -0.06
     Sterling
    -0.06
     Cand
    -0.06
     min
    -0.06
     probably
    -0.06
    .BASELINE
    -0.06
     onboard
    -0.06
     pure
    -0.06
    awai
    -0.05
    POSITIVE LOGITS
    kon
    0.12
    Kon
    0.12
    buzz
    0.11
    igraph
    0.11
    "?>↵
    0.11
     reordered
    0.11
    Ordered
    0.11
    cock
    0.11
     hypothesis
    0.11
    /template
    0.11
    Activations Density 0.070%

    No Known Activations