© 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. 16463
    Prev
    Next
    INDEX
    Explanations

    `this` or `that` followed by pronoun/determiner

    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
    apy
    -0.10
     revisit
    -0.09
    AJ
    -0.09
     revis
    -0.09
    abi
    -0.08
    ajs
    -0.08
    sons
    -0.08
     Myst
    -0.08
    aju
    -0.08
    aille
    -0.07
    POSITIVE LOGITS
     THAT
    0.30
     here
    0.20
     THIS
    0.17
     THEM
    0.17
     HERE
    0.17
     even
    0.16
     EVEN
    0.16
    here
    0.15
     ALSO
    0.15
     THERE
    0.15
    Activations Density 0.531%

    No Known Activations