© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 48976
    Prev
    Next
    INDEX
    Explanations

    recognizes / knows / realized

    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
     Tent
    -0.11
     Cri
    -0.10
     Mant
    -0.10
     Dez
    -0.10
    orum
    -0.10
    wahl
    -0.10
     Oliv
    -0.10
    dismiss
    -0.09
     writ
    -0.09
    elen
    -0.09
    POSITIVE LOGITS
     realized
    0.24
     recognized
    0.23
     realization
    0.22
     realizes
    0.21
     realize
    0.21
     realised
    0.21
     recognised
    0.21
     knows
    0.21
     knew
    0.21
     know
    0.20
    Activations Density 0.090%

    No Known Activations