© 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. 3931
    Prev
    Next
    INDEX
    Explanations

    aerobic

    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
    edb
    -0.11
     Surveillance
    -0.10
    apl
    -0.10
    uez
    -0.09
     iota
    -0.09
    Nib
    -0.09
    utt
    -0.09
    esi
    -0.08
    elsen
    -0.08
     congest
    -0.08
    POSITIVE LOGITS
    uche
    0.09
    nez
    0.09
    ety
    0.09
    nest
    0.09
    омеÑĢ
    0.09
    indy
    0.09
     Chick
    0.09
    jj
    0.09
    pie
    0.08
    -horizontal
    0.08
    Activations Density 0.004%

    No Known Activations