© 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. 5448
    Prev
    Next
    INDEX
    Explanations

    punctuation followed by continuation

    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
     fet
    -0.12
     NDP
    -0.12
    cdc
    -0.12
     adj
    -0.12
    laden
    -0.12
    eut
    -0.11
     Cain
    -0.11
    iage
    -0.11
    ilty
    -0.11
    uten
    -0.11
    POSITIVE LOGITS
     bonus
    0.08
     drum
    0.07
     hic
    0.07
     wait
    0.07
    Bonus
    0.07
     Bonus
    0.06
     dare
    0.06
     vo
    0.06
    appoint
    0.06
     conced
    0.06
    Activations Density 0.026%

    No Known Activations