© 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. 27449
    Prev
    Next
    INDEX
    Explanations

    appending "friendly" or "-ready"

    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
     Booker
    -0.07
     Sidney
    -0.07
    old
    -0.07
     inv
    -0.07
     Riley
    -0.07
     nothing
    -0.07
     suffering
    -0.07
     rein
    -0.07
    Hits
    -0.07
     over
    -0.07
    POSITIVE LOGITS
    ity
    0.15
    -cert
    0.14
    ITY
    0.14
    NESS
    0.13
    ness
    0.13
    æĢ§
    0.13
    -friendly
    0.13
     certified
    0.13
    /-
    0.12
     clothing
    0.12
    Activations Density 0.510%

    No Known Activations