© 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. 5085
    Prev
    Next
    INDEX
    Explanations

    Proper nouns or abbreviations starting with S

    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
    acom
    -0.11
     Mandal
    -0.11
     Elias
    -0.10
     Plex
    -0.10
     Lancaster
    -0.10
    jax
    -0.10
    alah
    -0.10
    IPC
    -0.10
     ank
    -0.09
     CPC
    -0.09
    POSITIVE LOGITS
     SDS
    0.17
     sug
    0.14
     Sprint
    0.14
     Sug
    0.13
     SSD
    0.13
     SD
    0.13
     Sawyer
    0.13
     SMP
    0.13
     getS
    0.13
     PSU
    0.13
    Activations Density 0.011%

    No Known Activations