© 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. 32143
    Prev
    Next
    INDEX
    Explanations

    possessive pronouns followed by associated 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
     Brace
    -0.09
     presence
    -0.09
     Burgess
    -0.09
    ugen
    -0.08
    resas
    -0.08
     aura
    -0.08
    presence
    -0.08
     latter
    -0.08
     aforementioned
    -0.08
     traged
    -0.07
    POSITIVE LOGITS
     mind
    0.18
     minds
    0.13
     thoughts
    0.12
     imagination
    0.12
     attention
    0.12
     overriding
    0.12
    mind
    0.12
     curiosity
    0.12
     glance
    0.11
     reflections
    0.11
    Activations Density 0.019%

    No Known Activations