© 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. 33540
    Prev
    Next
    INDEX
    Explanations

    customizer

    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
    xor
    -0.11
     Thor
    -0.11
    -turned
    -0.11
     learnt
    -0.11
    cid
    -0.11
    rophic
    -0.10
     Ur
    -0.10
     tan
    -0.10
    xa
    -0.10
     Willie
    -0.10
    POSITIVE LOGITS
    ï¸ı
    0.13
    orld
    0.07
     ump
    0.07
     rout
    0.06
    ↵↵↵↵↵↵↵↵↵↵↵↵↵↵
    0.06
     kn
    0.06
    _MSK
    0.06
     sut
    0.06
     Lux
    0.06
     ECC
    0.06
    Activations Density 1.707%

    No Known Activations