© 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. 5182
    Prev
    Next
    INDEX
    Explanations

    headlines or lists

    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
    iaux
    -0.09
    iband
    -0.09
    /tcp
    -0.08
    itra
    -0.08
    ubern
    -0.08
     ranks
    -0.08
     Alo
    -0.08
     conson
    -0.08
    ocab
    -0.07
    embro
    -0.07
    POSITIVE LOGITS
     artifact
    0.12
     Kemp
    0.10
     fixing
    0.10
     faint
    0.10
     toast
    0.10
     artifacts
    0.10
     aprove
    0.10
    Outcome
    0.09
     Haupt
    0.09
    abad
    0.09
    Activations Density 0.005%

    No Known Activations