© 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. 89551
    Prev
    Next
    INDEX
    Explanations

    be affected or be supported

    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
    504
    -0.09
    aint
    -0.09
    459
    -0.09
    hoot
    -0.08
    745
    -0.08
    pard
    -0.08
    olie
    -0.08
    mium
    -0.08
     lined
    -0.08
    Checkout
    -0.08
    POSITIVE LOGITS
    è¢
    0.35
     being
    0.23
     Being
    0.21
    being
    0.21
    ãģķãĤĮ
    0.18
    Being
    0.18
     receiving
    0.18
     receive
    0.18
     receives
    0.17
    -being
    0.16
    Activations Density 0.257%

    No Known Activations