© 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. 4343
    Prev
    Next
    INDEX
    Explanations

    possessive determiners followed by 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
     meis
    -0.09
    polit
    -0.09
    vari
    -0.08
    WRAPPER
    -0.08
     FW
    -0.08
     è¾ĵ
    -0.08
    abr
    -0.07
     amt
    -0.07
     Gods
    -0.07
    spiel
    -0.07
    POSITIVE LOGITS
    ķìĿ¸
    0.09
    Dyn
    0.09
    ungen
    0.09
     Sy
    0.09
    agged
    0.09
    §
    0.09
    emetery
    0.09
     deben
    0.09
    uni
    0.09
    errated
    0.09
    Activations Density 0.014%

    No Known Activations