© 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
    2. Olmo-3-1125-32B
    3. 32-RES-BATCHTOPK-131K
    4. 17981
    Prev
    Next
    INDEX
    Explanations

    constructor without argument

    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
    uft
    -0.11
    wik
    -0.10
    ordo
    -0.10
     Bez
    -0.10
    -any
    -0.10
     reserve
    -0.09
    addtogroup
    -0.09
    uby
    -0.09
    aub
    -0.09
    wend
    -0.09
    POSITIVE LOGITS
    ÛĮر
    0.08
     Sims
    0.08
     courteous
    0.08
     sque
    0.07
     tabs
    0.07
     stuffing
    0.07
    roids
    0.07
     scri
    0.07
     Jared
    0.07
     Conc
    0.07
    Activations Density 0.002%

    No Known Activations