© 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. 49859
    Prev
    Next
    INDEX
    Explanations

    blame or fault

    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
     complaining
    -0.11
     complains
    -0.11
     complained
    -0.11
     fault
    -0.11
    ker
    -0.11
     blames
    -0.10
     blamed
    -0.10
     accused
    -0.10
     Fault
    -0.10
    ava
    -0.10
    POSITIVE LOGITS
     wholly
    0.10
     entirely
    0.10
     NONE
    0.10
     share
    0.09
     ðŁij
    0.09
    UIL
    0.09
     solely
    0.09
     Huntington
    0.08
     McMaster
    0.08
     whirl
    0.08
    Activations Density 0.033%

    No Known Activations