© 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. 114464
    Prev
    Next
    INDEX
    Explanations

    existential quantifier 'there are'

    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
    553
    -0.11
     most
    -0.09
    igm
    -0.09
     Most
    -0.09
     crave
    -0.08
    Highlights
    -0.08
    Most
    -0.08
     motivated
    -0.07
     only
    -0.07
     Highlights
    -0.07
    POSITIVE LOGITS
     ones
    0.18
     instances
    0.17
     cases
    0.16
     versions
    0.14
     several
    0.14
     occasions
    0.14
     Ones
    0.13
     Instances
    0.13
    ä¸ĵ
    0.13
     specialized
    0.13
    Activations Density 0.438%

    No Known Activations