© 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. 91496
    Prev
    Next
    INDEX
    Explanations

    other people or groups

    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
    niest
    -0.08
    /account
    -0.08
    /screen
    -0.08
    lé
    -0.08
     earliest
    -0.08
    vous
    -0.08
     Spears
    -0.08
     some
    -0.08
     widest
    -0.08
    elters
    -0.08
    POSITIVE LOGITS
     aspects
    0.15
     people
    0.15
     things
    0.15
     parts
    0.14
     forms
    0.14
     peoples
    0.13
     kinds
    0.13
    wis
    0.12
    wi
    0.12
     areas
    0.12
    Activations Density 0.082%

    No Known Activations