© 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. 31304
    Prev
    Next
    INDEX
    Explanations

    X and later/older/newer/more

    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
     Sk
    -0.11
    iten
    -0.10
     slack
    -0.10
    Brains
    -0.09
    otas
    -0.09
    /to
    -0.09
    ·»
    -0.09
    ulle
    -0.09
     Permanent
    -0.09
    ito
    -0.09
    POSITIVE LOGITS
     beyond
    0.40
     onwards
    0.33
    以ä¸Ĭ
    0.32
     onward
    0.30
     Beyond
    0.29
    Beyond
    0.26
     above
    0.26
     higher
    0.25
     upwards
    0.24
     greater
    0.22
    Activations Density 0.293%

    No Known Activations