© 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. 89469
    Prev
    Next
    INDEX
    Explanations

    such as

    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
     myself
    -0.18
     oft
    -0.16
     countless
    -0.12
     pertaining
    -0.12
     whatsoever
    -0.12
     I
    -0.11
     ourselves
    -0.11
     harb
    -0.11
    ilst
    -0.11
     Budd
    -0.10
    POSITIVE LOGITS
     Yo
    0.11
    asts
    0.10
    yo
    0.10
    FU
    0.09
     Fake
    0.09
     yo
    0.09
     Shib
    0.09
     uncon
    0.09
     unhappy
    0.09
     Kund
    0.09
    Activations Density 0.015%

    No Known Activations