© 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. 14546
    Prev
    Next
    INDEX
    Explanations

    commonly referred to as or just

    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
    cpy
    -0.09
    alth
    -0.08
    obi
    -0.08
    ior
    -0.08
    /apis
    -0.08
     acting
    -0.08
     Hass
    -0.08
     essentially
    -0.08
     Gateway
    -0.08
    arkan
    -0.07
    POSITIVE LOGITS
     simply
    0.41
     Simply
    0.26
    Simply
    0.26
     shortened
    0.25
     simplement
    0.23
     shorten
    0.22
     just
    0.22
     plain
    0.20
     shorter
    0.18
     einfach
    0.17
    Activations Density 0.383%

    No Known Activations