© 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
    2. Olmo-3-1125-32B
    3. 32-RES-BATCHTOPK-131K
    4. 26967
    Prev
    Next
    INDEX
    Explanations

    financial costs and consequences

    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
    —they
    -0.16
    —it
    -0.15
    )])↵↵
    -0.13
    —he
    -0.12
    —we
    -0.12
    ;}↵↵
    -0.12
    ;/*
    -0.12
     ;)↵↵
    -0.12
    ))))↵↵
    -0.12
    ]])↵↵
    -0.12
    POSITIVE LOGITS
    å¹¶
    0.12
    ï¼Įå¹¶
    0.12
     while
    0.12
    ").
    0.11
    ').
    0.11
     amd
    0.10
     ).
    0.10
     ").
    0.10
    ".
    0.09
    .).
    0.09
    Activations Density 3.825%

    No Known Activations