© 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. 15692
    Prev
    Next
    INDEX
    Explanations

    question marks and exclamation points

    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
    rans
    -0.08
    ogo
    -0.07
    ican
    -0.07
     otherwise
    -0.07
    unan
    -0.07
     Dove
    -0.07
     trans
    -0.07
     #(
    -0.07
    uw
    -0.07
     irrelevant
    -0.07
    POSITIVE LOGITS
     shm
    0.12
    appable
    0.12
     scarcity
    0.11
     hardly
    0.11
     Fat
    0.11
    ?!
    0.11
    !?
    0.11
    ?
    0.11
     surpassed
    0.11
    åĶ
    0.11
    Activations Density 0.032%

    No Known Activations