© 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. 50586
    Prev
    Next
    INDEX
    Explanations

    I think/feel/mean

    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
     awaits
    -0.11
     apologies
    -0.11
     kindly
    -0.10
     SHALL
    -0.10
     shall
    -0.10
     hereby
    -0.10
     semiclass
    -0.10
     rightly
    -0.10
    aff
    -0.10
     proced
    -0.10
    POSITIVE LOGITS
     think
    0.15
     mean
    0.12
     don
    0.11
     said
    0.11
     liken
    0.11
     thinks
    0.10
    Think
    0.10
     feel
    0.10
     Think
    0.10
     felt
    0.10
    Activations Density 0.135%

    No Known Activations