© 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. 111815
    Prev
    Next
    INDEX
    Explanations

    his, her, their, its

    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
    them
    -0.10
     dbs
    -0.10
     them
    -0.10
    sta
    -0.09
    asion
    -0.08
    USR
    -0.08
     sta
    -0.08
    afb
    -0.08
    propri
    -0.08
     ours
    -0.08
    POSITIVE LOGITS
     his
    0.25
    his
    0.23
     their
    0.19
     its
    0.19
     его
    0.18
    their
    0.18
    His
    0.17
     THEIR
    0.17
     her
    0.16
    Its
    0.16
    Activations Density 0.511%

    No Known Activations