© 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. 46670
    Prev
    Next
    INDEX
    Explanations

    knees

    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
    oust
    -0.11
    aceous
    -0.11
    åı£
    -0.11
    UPS
    -0.10
     festive
    -0.10
    :model
    -0.10
    uem
    -0.10
     Palo
    -0.10
     hand
    -0.10
    UBE
    -0.10
    POSITIVE LOGITS
    DR
    0.08
     astr
    0.08
     bri
    0.07
    inks
    0.07
     Imagine
    0.07
     ground
    0.07
     calf
    0.07
     Wak
    0.07
    mere
    0.07
     bog
    0.07
    Activations Density 0.003%

    No Known Activations