© 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. 7552
    Prev
    Next
    INDEX
    Explanations

    alternative, knowledge, representation, sexual, shopper

    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
     dov
    -0.12
     champs
    -0.10
     austerity
    -0.10
    .getSimpleName
    -0.10
     Romero
    -0.09
     grandson
    -0.09
     installs
    -0.09
     Madison
    -0.09
    ."↵↵↵↵
    -0.09
     testimonials
    -0.09
    POSITIVE LOGITS
    dda
    0.10
     replay
    0.09
     ur
    0.09
     shout
    0.08
    atus
    0.08
     sne
    0.08
     projectile
    0.08
     Mare
    0.08
     paddle
    0.08
     favor
    0.08
    Activations Density 0.016%

    No Known Activations