© 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. 4925
    Prev
    Next
    INDEX
    Explanations

    now or immediately

    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
     lately
    -0.11
    zzle
    -0.10
    idi
    -0.09
    orr
    -0.09
    adam
    -0.09
     increasingly
    -0.09
     Ramp
    -0.08
     ramps
    -0.08
     ramp
    -0.08
    ollo
    -0.08
    POSITIVE LOGITS
     immediately
    0.39
     NOW
    0.36
     immedi
    0.32
     immediate
    0.32
     now
    0.30
    NOW
    0.29
     Immediately
    0.29
     Immediate
    0.27
     today
    0.27
     TODAY
    0.26
    Activations Density 0.269%

    No Known Activations