© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 27131
    Prev
    Next
    INDEX
    Explanations

    trying to find

    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
    retch
    -0.11
    ãĥ¼ãĤ¹
    -0.11
     {-
    -0.11
     ä
    -0.10
    cheme
    -0.10
    ate
    -0.10
    ",-
    -0.10
    cene
    -0.09
    uler
    -0.09
     Screens
    -0.09
    POSITIVE LOGITS
     hoping
    0.12
     find
    0.10
     hoped
    0.10
    æī¾
    0.09
     ascertain
    0.09
     crest
    0.09
     somehow
    0.09
     assure
    0.09
     ensure
    0.09
    .Find
    0.09
    Activations Density 0.045%

    No Known Activations