© 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. 112584
    Prev
    Next
    INDEX
    Explanations

    pull up

    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
     reopening
    -0.09
    nst
    -0.08
     withdraw
    -0.08
     rer
    -0.08
    Opened
    -0.08
     slit
    -0.08
     retros
    -0.07
     bomb
    -0.07
     Bil
    -0.07
     PUSH
    -0.07
    POSITIVE LOGITS
    /dr
    0.12
     into
    0.12
    _drive
    0.12
     INTO
    0.12
    itzer
    0.12
     Depart
    0.12
     arrive
    0.11
    inder
    0.11
     depart
    0.11
     farther
    0.11
    Activations Density 0.005%

    No Known Activations