© 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. 89212
    Prev
    Next
    INDEX
    Explanations

    make a point to

    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
     tricks
    -0.09
     prospect
    -0.08
     opts
    -0.08
    405
    -0.08
     concaten
    -0.08
     decide
    -0.08
     luck
    -0.07
     lucky
    -0.07
     outright
    -0.07
     aspire
    -0.07
    POSITIVE LOGITS
     remind
    0.13
     ((!
    0.12
    bh
    0.11
     neither
    0.11
     CSC
    0.11
     Mention
    0.10
    ucer
    0.10
    shal
    0.10
    ISP
    0.10
    reh
    0.10
    Activations Density 0.010%

    No Known Activations