© 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. 30142
    Prev
    Next
    INDEX
    Explanations

    expected behavior

    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
    cock
    -0.10
     twee
    -0.10
    olin
    -0.10
    /arch
    -0.10
     turret
    -0.09
    hart
    -0.09
     gloss
    -0.09
     reopening
    -0.09
    ven
    -0.09
    uncan
    -0.08
    POSITIVE LOGITS
     perfectly
    0.29
     correctly
    0.28
     accurately
    0.23
     perfect
    0.22
     exactly
    0.21
    perfect
    0.21
     correct
    0.20
     appropriately
    0.20
     Perfect
    0.19
    æŃ£ç¡®
    0.19
    Activations Density 0.616%

    No Known Activations