© 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. 48834
    Prev
    Next
    INDEX
    Explanations

    just a thought or idea

    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
    linger
    -0.10
     Fund
    -0.10
    ahr
    -0.10
     Nin
    -0.09
     tack
    -0.09
     NRA
    -0.09
    OI
    -0.09
     Singles
    -0.09
     Fully
    -0.09
     Cout
    -0.09
    POSITIVE LOGITS
    ãĥ³ãĥĪ
    0.10
    ioned
    0.09
     excuse
    0.09
     spiele
    0.09
     salute
    0.09
     rol
    0.09
     roar
    0.09
    YM
    0.09
    esus
    0.09
    yms
    0.08
    Activations Density 0.001%

    No Known Activations