© 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. 88489
    Prev
    Next
    INDEX
    Explanations

    All Rights Reserved

    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
    edor
    -0.12
     solo
    -0.10
    jak
    -0.10
    FullScreen
    -0.09
    zu
    -0.09
    azen
    -0.09
    Pinterest
    -0.09
     Meg
    -0.09
     roz
    -0.09
    012
    -0.09
    POSITIVE LOGITS
     entitlement
    0.07
     unlike
    0.07
     Nash
    0.07
     babys
    0.07
    yk
    0.07
     fri
    0.07
     Highland
    0.07
    atab
    0.07
     Lar
    0.07
     burden
    0.06
    Activations Density 0.001%

    No Known Activations