© 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. 27297
    Prev
    Next
    INDEX
    Explanations

    possessive pronouns followed by nouns

    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
     missing
    -0.11
     problematic
    -0.10
     objection
    -0.09
    uzz
    -0.09
    ollo
    -0.09
     fen
    -0.08
    quier
    -0.08
    ows
    -0.08
    ìĨ
    -0.08
     Missing
    -0.08
    POSITIVE LOGITS
     promised
    0.14
     seams
    0.14
     attempts
    0.13
     formerly
    0.13
     credibility
    0.13
     Worse
    0.12
     Attempts
    0.12
     morale
    0.12
     attempt
    0.12
     promising
    0.12
    Activations Density 0.323%

    No Known Activations