© 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. 5113
    Prev
    Next
    INDEX
    Explanations

    resolution or rate settings

    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
    418
    -0.09
     Gamer
    -0.09
     perman
    -0.09
    bsd
    -0.09
     slo
    -0.08
    AGES
    -0.08
    Rotate
    -0.08
     escap
    -0.08
     disin
    -0.08
    isplay
    -0.08
    POSITIVE LOGITS
    /frame
    0.11
     Mish
    0.11
    mites
    0.10
     Lum
    0.10
     Depths
    0.09
     Wahl
    0.09
     Hollywood
    0.09
     Stephan
    0.09
    ogh
    0.09
     orgy
    0.09
    Activations Density 0.013%

    No Known Activations