© 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. 47812
    Prev
    Next
    INDEX
    Explanations

    hope you

    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
     kissing
    -0.10
    qs
    -0.09
     competing
    -0.09
     Compet
    -0.09
    unga
    -0.09
     indis
    -0.09
     unwilling
    -0.08
     Dear
    -0.08
     mo
    -0.08
    scp
    -0.08
    POSITIVE LOGITS
     enjoy
    0.20
     enjoyed
    0.20
     enjoys
    0.17
     liked
    0.17
     enjoying
    0.16
     pardon
    0.15
    liked
    0.14
     agree
    0.13
     find
    0.13
     excuse
    0.13
    Activations Density 0.026%

    No Known Activations