© 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. 32357
    Prev
    Next
    INDEX
    Explanations

    being a

    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
     Lug
    -0.11
     hoping
    -0.11
     willing
    -0.11
     gladly
    -0.09
     eager
    -0.09
     wanting
    -0.09
    angel
    -0.09
     expecting
    -0.09
     refusing
    -0.09
     unwilling
    -0.08
    POSITIVE LOGITS
     outdoors
    0.15
     surrounded
    0.14
     alone
    0.12
     indoors
    0.12
     pam
    0.12
     solitude
    0.11
     centre
    0.11
     spotlight
    0.11
     Dexter
    0.11
     underst
    0.11
    Activations Density 0.011%

    No Known Activations