© 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. 33157
    Prev
    Next
    INDEX
    Explanations

    GMT+0000 (UTC)

    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
     Petr
    -0.10
     spell
    -0.10
     Bergen
    -0.09
     SPELL
    -0.09
    STD
    -0.09
    gra
    -0.09
     disput
    -0.09
     triplet
    -0.09
    spell
    -0.09
     Montgomery
    -0.09
    POSITIVE LOGITS
     nib
    0.09
     bypass
    0.08
     rotation
    0.08
     Dough
    0.08
    amer
    0.08
     RF
    0.08
     Kah
    0.08
     mythology
    0.08
     NON
    0.08
     Ideal
    0.08
    Activations Density 0.001%

    No Known Activations