© 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. 7546
    Prev
    Next
    INDEX
    Explanations

    layer of plaster, soil, area of tissue

    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
     Charm
    -0.07
    âĢ¦I
    -0.07
     consenting
    -0.07
    ta
    -0.07
     strip
    -0.07
     CWE
    -0.07
    at
    -0.07
     Suff
    -0.07
     Sem
    -0.06
    ivos
    -0.06
    POSITIVE LOGITS
     ihrem
    0.12
     goodies
    0.11
     granularity
    0.11
    ?>↵↵↵
    0.11
    è¯Ŀ
    0.11
     negativity
    0.11
    (&(
    0.11
     the
    0.11
    mess
    0.10
     their
    0.10
    Activations Density 0.185%

    No Known Activations