© 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. 28206
    Prev
    Next
    INDEX
    Explanations

    greeting and address

    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
     Recorder
    -0.09
     --
    -0.08
    mal
    -0.08
    urm
    -0.08
    ippy
    -0.08
     workflow
    -0.08
     pair
    -0.08
    amarin
    -0.08
    749
    -0.08
    odie
    -0.08
    POSITIVE LOGITS
     gentlemen
    0.13
     inert
    0.13
     Gent
    0.12
     Dolphin
    0.12
     Este
    0.12
    -messages
    0.12
     guys
    0.11
     respectable
    0.10
     dilig
    0.10
     Tmin
    0.10
    Activations Density 0.007%

    No Known Activations