© 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. 27650
    Prev
    Next
    INDEX
    Explanations

    if one anything

    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
     Zah
    -0.13
     nothing
    -0.12
    nothing
    -0.12
     nada
    -0.11
    556
    -0.11
    /buttons
    -0.10
    ble
    -0.10
     Nothing
    -0.10
    anke
    -0.10
     comb
    -0.10
    POSITIVE LOGITS
     limp
    0.09
     purge
    0.09
    oku
    0.08
    kek
    0.08
     Barg
    0.08
     Kv
    0.08
     credit
    0.08
     burst
    0.07
     Nights
    0.07
    eff
    0.07
    Activations Density 0.001%

    No Known Activations