© 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. 16985
    Prev
    Next
    INDEX
    Explanations

    working together

    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
     itself
    -0.11
    etus
    -0.09
    unic
    -0.09
    aval
    -0.09
    andel
    -0.09
     Parade
    -0.09
    anje
    -0.09
     undone
    -0.09
    acci
    -0.08
    ossier
    -0.08
    POSITIVE LOGITS
     alike
    0.27
     respectively
    0.26
     themselves
    0.26
     together
    0.26
     jointly
    0.22
     Together
    0.19
    gether
    0.18
    Together
    0.16
     respective
    0.16
     mutually
    0.15
    Activations Density 0.275%

    No Known Activations