© 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. 32409
    Prev
    Next
    INDEX
    Explanations

    if you

    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
     succeed
    -0.12
    -success
    -0.12
    indr
    -0.11
     successful
    -0.11
    isia
    -0.11
     toda
    -0.10
     fortunately
    -0.10
    .success
    -0.10
     acknow
    -0.10
     worthy
    -0.10
    POSITIVE LOGITS
     anyone
    0.10
     used
    0.10
     you
    0.09
     intending
    0.09
    used
    0.09
     anybody
    0.09
     susp
    0.09
     attempting
    0.08
     youre
    0.08
     Used
    0.08
    Activations Density 0.082%

    No Known Activations