© 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. 47191
    Prev
    Next
    INDEX
    Explanations

    per se

    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
     subt
    -0.09
    imd
    -0.08
     convinc
    -0.08
     due
    -0.08
     Brow
    -0.07
     precedence
    -0.07
     ath
    -0.07
    æĺĵ
    -0.07
     Dunn
    -0.07
    Bounding
    -0.07
    POSITIVE LOGITS
     itself
    0.31
     inherently
    0.22
     Alone
    0.20
     harmless
    0.20
     intrinsic
    0.19
     alone
    0.19
     qua
    0.18
     themselves
    0.18
     inherent
    0.17
     perse
    0.16
    Activations Density 0.497%

    No Known Activations