© 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. 7659
    Prev
    Next
    INDEX
    Explanations

    pronoun + verb

    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
    ADATA
    -0.09
    ards
    -0.08
     dro
    -0.08
    <|fim_middle|>
    -0.08
    ec
    -0.08
    aggi
    -0.08
    tere
    -0.08
    pp
    -0.08
     Bruno
    -0.08
     Closed
    -0.08
    POSITIVE LOGITS
    .toInt
    0.09
     Bulg
    0.09
     intellectually
    0.09
    âĢİ
    0.08
    anus
    0.08
     garg
    0.08
    porter
    0.08
    ALAR
    0.08
     monumental
    0.08
    POOL
    0.08
    Activations Density 0.220%

    No Known Activations