© 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. 3850
    Prev
    Next
    INDEX
    Explanations

    each time

    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
     Clifford
    -0.09
    anes
    -0.09
     everything
    -0.08
     [:
    -0.08
    everything
    -0.08
     EVERY
    -0.08
     unr
    -0.07
    985
    -0.07
     every
    -0.07
    kind
    -0.07
    POSITIVE LOGITS
     morning
    0.13
     time
    0.12
     whenever
    0.12
    Whenever
    0.11
     vez
    0.11
    fal
    0.11
     khi
    0.11
     Valent
    0.10
    -inline
    0.10
     Vine
    0.10
    Activations Density 0.027%

    No Known Activations