© 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. 88453
    Prev
    Next
    INDEX
    Explanations

    possessive noun or pronoun followed by descriptor

    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
     inherently
    -0.11
    china
    -0.11
    markdown
    -0.11
     nowhere
    -0.10
    Found
    -0.10
     Sommer
    -0.10
    equal
    -0.10
    nsic
    -0.10
    ipt
    -0.10
    edit
    -0.10
    POSITIVE LOGITS
     approximate
    0.17
     total
    0.17
     maximum
    0.16
     average
    0.14
     estimated
    0.13
     abbreviation
    0.13
     motto
    0.13
     predominant
    0.12
     minimum
    0.12
     name
    0.12
    Activations Density 0.970%

    No Known Activations