© 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. 6444
    Prev
    Next
    INDEX
    Explanations

    number of years

    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
    DIC
    -0.10
    /id
    -0.09
     ultimate
    -0.09
     recovery
    -0.09
    asher
    -0.09
    avana
    -0.09
     hamm
    -0.09
     raft
    -0.09
     god
    -0.08
     transmitter
    -0.08
    POSITIVE LOGITS
     Bangalore
    0.14
    India
    0.13
     atleast
    0.12
     India
    0.12
    bose
    0.11
     Chennai
    0.11
     Rao
    0.11
     Indian
    0.11
     till
    0.10
     GANG
    0.10
    Activations Density 0.480%

    No Known Activations