© 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. 4160
    Prev
    Next
    INDEX
    Explanations

    possessive pronouns followed by family/relationships

    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
     Families
    -0.10
    rium
    -0.10
     families
    -0.09
    locs
    -0.09
     Souls
    -0.09
     Mond
    -0.09
    &e
    -0.08
     Swe
    -0.08
    rud
    -0.08
    Locator
    -0.08
    POSITIVE LOGITS
     supposedly
    0.18
     supposed
    0.13
     respected
    0.11
     guidance
    0.11
     narrowly
    0.10
     nightmare
    0.10
     skinny
    0.10
     suspicions
    0.10
     neighb
    0.10
     trusted
    0.10
    Activations Density 0.046%

    No Known Activations