© 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. 29317
    Prev
    Next
    INDEX
    Explanations

    even

    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
     unfortunately
    -0.14
     even
    -0.13
     MAY
    -0.13
     sadly
    -0.12
     despite
    -0.12
     regardless
    -0.11
     anyways
    -0.11
     notwithstanding
    -0.11
     Unfortunately
    -0.11
    ots
    -0.10
    POSITIVE LOGITS
    steen
    0.09
    itti
    0.09
     knew
    0.09
    omat
    0.09
     outnumber
    0.08
     sensed
    0.08
     Ashley
    0.08
     unfinished
    0.08
     plainly
    0.08
     contagious
    0.08
    Activations Density 0.042%

    No Known Activations