© 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. 115764
    Prev
    Next
    INDEX
    Explanations

    possessive 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
    esium
    -0.09
    urous
    -0.09
    cline
    -0.09
     (('
    -0.09
    OWN
    -0.09
     Middleton
    -0.08
    ocale
    -0.08
    owell
    -0.08
     dram
    -0.08
     Soph
    -0.08
    POSITIVE LOGITS
    (s
    0.21
    /part
    0.15
    's
    0.13
    /student
    0.12
    ’s
    0.12
    upal
    0.12
    /client
    0.12
     yourselves
    0.12
    /player
    0.11
    (es
    0.10
    Activations Density 0.035%

    No Known Activations