© 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. 49485
    Prev
    Next
    INDEX
    Explanations

    button click/tap

    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
     Wand
    -0.10
     sublist
    -0.09
    jas
    -0.09
     vern
    -0.09
    ille
    -0.09
     surpr
    -0.08
    /he
    -0.08
     domic
    -0.08
    riages
    -0.08
     Timber
    -0.08
    POSITIVE LOGITS
     pressed
    0.21
     presses
    0.19
    _pressed
    0.19
    Pressed
    0.18
     press
    0.17
     onPressed
    0.16
    pressed
    0.15
     pushed
    0.15
     push
    0.14
    press
    0.14
    Activations Density 0.191%

    No Known Activations