© 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. 89956
    Prev
    Next
    INDEX
    Explanations

    with [something]

    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
     altern
    -0.11
    rine
    -0.11
     greatness
    -0.11
    /th
    -0.11
    mgr
    -0.10
    hof
    -0.10
    Asked
    -0.10
     fascination
    -0.10
    ÑģÑı
    -0.10
    anked
    -0.09
    POSITIVE LOGITS
     help
    0.11
     our
    0.10
     ease
    0.10
     regards
    0.10
     apl
    0.09
     Help
    0.09
     Hindered
    0.09
    standing
    0.09
     Cah
    0.09
     Guar
    0.09
    Activations Density 0.041%

    No Known Activations