© 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. 49564
    Prev
    Next
    INDEX
    Explanations

    Questions asking for confirmation or possibility

    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
    vor
    -0.09
    CV
    -0.09
    acd
    -0.09
     Commonwealth
    -0.09
     sympathetic
    -0.09
    imi
    -0.09
     CI
    -0.09
     sympath
    -0.09
     addicted
    -0.09
     Why
    -0.09
    POSITIVE LOGITS
     consent
    0.12
     approved
    0.11
     Confirm
    0.11
     confirm
    0.11
    confirm
    0.10
     Consent
    0.10
    -ok
    0.10
     acceptable
    0.10
     authorised
    0.10
     Desired
    0.10
    Activations Density 0.018%

    No Known Activations