© 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. 6199
    Prev
    Next
    INDEX
    Explanations

    how ... to

    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
     actually
    -0.10
    idan
    -0.10
     REALLY
    -0.09
    inator
    -0.09
    vida
    -0.09
    uez
    -0.09
    vak
    -0.08
    elly
    -0.08
     probably
    -0.08
    oka
    -0.08
    POSITIVE LOGITS
     slo
    0.10
     else
    0.10
     anymore
    0.10
    ovel
    0.09
    would
    0.09
     would
    0.09
    Ĥ
    0.09
     unintention
    0.09
     Pik
    0.09
     slowed
    0.09
    Activations Density 0.071%

    No Known Activations