© 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. 28049
    Prev
    Next
    INDEX
    Explanations

    Oracle and licensing

    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
     Ding
    -0.09
    inkle
    -0.08
     Herald
    -0.08
     Mine
    -0.08
     Trophy
    -0.08
    pulse
    -0.08
     showroom
    -0.08
    ugo
    -0.08
     stagnant
    -0.08
    fil
    -0.07
    POSITIVE LOGITS
     paired
    0.11
     nib
    0.10
     coupled
    0.10
    ')+
    0.10
     congr
    0.10
    erno
    0.09
    urally
    0.09
    olar
    0.09
     Bj
    0.09
    Su
    0.09
    Activations Density 0.004%

    No Known Activations