© 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. 114248
    Prev
    Next
    INDEX
    Explanations

    negation followed by action or state

    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
    heit
    -0.08
     barg
    -0.08
    ero
    -0.08
     ponder
    -0.08
     anonymously
    -0.07
     Benchmark
    -0.07
    961
    -0.07
     chore
    -0.07
     anonymous
    -0.07
    Benchmark
    -0.07
    POSITIVE LOGITS
    czy
    0.11
    inki
    0.11
    indi
    0.11
    -CS
    0.11
     seeming
    0.11
     accepted
    0.11
     domicile
    0.10
     accepting
    0.10
     pronounce
    0.10
     sexual
    0.10
    Activations Density 0.096%

    No Known Activations