© 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. 5022
    Prev
    Next
    INDEX
    Explanations

    despite being

    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
    cour
    -0.10
     courte
    -0.10
    zon
    -0.09
    dere
    -0.09
     Disc
    -0.09
     arrog
    -0.09
     unnoticed
    -0.09
     Kos
    -0.09
    .basic
    -0.09
    ablo
    -0.09
    POSITIVE LOGITS
     dearly
    0.15
     undes
    0.13
     truly
    0.13
     despite
    0.12
     genuinely
    0.12
     sincerely
    0.11
     notwithstanding
    0.11
     âĿ¤
    0.11
    Despite
    0.10
     Despite
    0.10
    Activations Density 0.060%

    No Known Activations