© 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. 91009
    Prev
    Next
    INDEX
    Explanations

    possessive suffix 's

    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
    osi
    -0.09
    544
    -0.09
     occurring
    -0.08
     WHATSOEVER
    -0.07
     usu
    -0.07
    kick
    -0.07
     Niet
    -0.07
     Pai
    -0.07
     Reese
    -0.07
     Bliss
    -0.07
    POSITIVE LOGITS
    's
    0.24
     versus
    0.20
    ’s
    0.20
     vs
    0.19
     learns
    0.16
    `s
    0.16
     Gets
    0.15
    ´s
    0.15
     Goes
    0.15
     revis
    0.14
    Activations Density 0.105%

    No Known Activations