© 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. 46979
    Prev
    Next
    INDEX
    Explanations

    possessive pronouns and associated 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
    ses
    -0.16
    —with
    -0.13
    —to
    -0.12
     fray
    -0.12
    —in
    -0.12
    tas
    -0.11
    —including
    -0.11
    —if
    -0.11
    ì¹ĺ
    -0.11
    ught
    -0.11
    POSITIVE LOGITS
    oret
    0.15
    odor
    0.15
    ories
    0.14
     inability
    0.11
    orem
    0.11
    oretical
    0.10
     Result
    0.09
     enorme
    0.09
     simplicity
    0.09
    olog
    0.08
    Activations Density 0.032%

    No Known Activations