© 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. 115635
    Prev
    Next
    INDEX
    Explanations

    containers and packaging

    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
    upp
    -0.11
     compliment
    -0.11
     unpack
    -0.10
     Nas
    -0.10
     Sparks
    -0.09
    OOT
    -0.09
    .fe
    -0.09
     Arrival
    -0.09
    Generating
    -0.09
     OPS
    -0.09
    POSITIVE LOGITS
     heading
    0.18
     Heading
    0.14
     headed
    0.13
    heading
    0.11
    Heading
    0.11
    -heading
    0.10
    ngo
    0.09
    agi
    0.09
     leading
    0.09
     deported
    0.09
    Activations Density 0.080%

    No Known Activations