© 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. 88728
    Prev
    Next
    INDEX
    Explanations

    font

    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
    oral
    -0.09
    еж
    -0.08
    per
    -0.08
     tether
    -0.08
    -io
    -0.08
    odox
    -0.08
     Blind
    -0.08
    Nit
    -0.08
     rud
    -0.08
    inel
    -0.08
    POSITIVE LOGITS
    asel
    0.10
     dime
    0.10
     luxury
    0.09
     Bosch
    0.09
     exotic
    0.09
     penny
    0.09
     Bose
    0.09
     luxurious
    0.09
     stor
    0.09
     vintage
    0.09
    Activations Density 0.002%

    No Known Activations