© 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. 90769
    Prev
    Next
    INDEX
    Explanations

    significantly improved or changed outcomes

    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
     Gregg
    -0.12
     McGr
    -0.12
     Probably
    -0.12
    æĦŁ
    -0.12
     probably
    -0.11
     circa
    -0.11
     Gilles
    -0.11
     Due
    -0.11
    uci
    -0.11
     someday
    -0.11
    POSITIVE LOGITS
     significantly
    0.13
     unanimously
    0.10
     consistently
    0.10
     (.
    0.10
     tended
    0.10
     regardless
    0.09
     showed
    0.09
     did
    0.09
     statistically
    0.09
     ONLY
    0.09
    Activations Density 2.168%

    No Known Activations