© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 113430
    Prev
    Next
    INDEX
    Explanations

    ISO standards

    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
     stats
    -0.09
     Stats
    -0.08
    adan
    -0.08
    printStats
    -0.07
     spat
    -0.07
    aken
    -0.07
     Bau
    -0.07
     beloved
    -0.07
    nip
    -0.07
    eker
    -0.07
    POSITIVE LOGITS
    Anywhere
    0.11
    hin
    0.11
    altitude
    0.10
     existential
    0.10
    apr
    0.10
     deferred
    0.10
    ç¡®
    0.10
     Lexer
    0.10
     plac
    0.10
    asn
    0.10
    Activations Density 0.008%

    No Known Activations