© 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. 27314
    Prev
    Next
    INDEX
    Explanations

    basic greetings

    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
    aces
    -0.11
    ':''
    -0.11
    .localized
    -0.11
    #ac
    -0.11
     remake
    -0.10
     oversh
    -0.10
     Homo
    -0.10
     Snowden
    -0.10
     Bare
    -0.10
     Orient
    -0.10
    POSITIVE LOGITS
     there
    0.11
     im
    0.10
     thank
    0.09
     I
    0.09
    ,I
    0.09
     client
    0.08
     caller
    0.08
    erv
    0.08
     thanks
    0.08
     cor
    0.08
    Activations Density 0.014%

    No Known Activations