© 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. 29274
    Prev
    Next
    INDEX
    Explanations

    much less

    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
     meanwhile
    -0.10
     undoubtedly
    -0.09
     moreover
    -0.09
     furthermore
    -0.08
     certainly
    -0.08
    /c
    -0.08
    izen
    -0.07
     instead
    -0.07
     likewise
    -0.07
     Alexandre
    -0.07
    POSITIVE LOGITS
     anything
    0.13
     any
    0.11
     mention
    0.11
     knew
    0.11
     knowing
    0.11
     bothering
    0.10
     bothered
    0.10
     anybody
    0.10
     participated
    0.10
    (any
    0.10
    Activations Density 0.002%

    No Known Activations