© 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. 17556
    Prev
    Next
    INDEX
    Explanations

    .us websites or phones

    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
     kron
    -0.10
    ieber
    -0.10
     airborne
    -0.10
     Ragnar
    -0.09
    idge
    -0.09
    leet
    -0.09
     Jur
    -0.09
     bcm
    -0.09
     alright
    -0.09
     Harlem
    -0.09
    POSITIVE LOGITS
    folk
    0.09
    è²
    0.09
     Shortcut
    0.08
     incidents
    0.08
    antas
    0.08
     boil
    0.08
     collar
    0.08
    151
    0.08
    asic
    0.08
     Jacobs
    0.08
    Activations Density 0.001%

    No Known Activations