© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 26821
    Prev
    Next
    INDEX
    Explanations

    but followed by pronoun or noun

    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
     Lud
    -0.10
     majority
    -0.10
     clearly
    -0.10
    Clearly
    -0.10
     Bever
    -0.10
     CLEAR
    -0.10
     plainly
    -0.10
     Exp
    -0.09
     lighter
    -0.09
     frankly
    -0.09
    POSITIVE LOGITS
     Effective
    0.12
     complications
    0.12
     somehow
    0.11
     devil
    0.11
     effective
    0.11
     complexities
    0.10
     implications
    0.10
     Unique
    0.10
     nuanced
    0.10
     complicated
    0.10
    Activations Density 0.254%

    No Known Activations