© 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. 113136
    Prev
    Next
    INDEX
    Explanations

    unfettered, misfolded, discarded, burned, detrended

    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
    ness
    -0.09
    ity
    -0.09
    eness
    -0.08
    ém
    -0.08
    ÑģÑĤÑĮ
    -0.08
    è¯Ŀ
    -0.07
    eliness
    -0.07
    isle
    -0.07
    anny
    -0.07
    ucid
    -0.07
    POSITIVE LOGITS
    ed
    1.04
    edBy
    0.54
    edb
    0.46
    edm
    0.40
    edata
    0.34
    ED
    0.34
    edd
    0.30
    edad
    0.29
    edly
    0.29
    edx
    0.29
    Activations Density 0.899%

    No Known Activations