© 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. 47832
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions

    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
    upe
    -0.13
     lokal
    -0.11
     typ
    -0.10
     dese
    -0.10
    kont
    -0.09
    wahl
    -0.09
     Soc
    -0.09
    inh
    -0.09
    uppen
    -0.09
    indr
    -0.09
    POSITIVE LOGITS
     sup
    0.10
     alike
    0.09
    sl
    0.08
     stir
    0.08
     sliding
    0.08
    åķĨ
    0.08
     sensitive
    0.07
     irrespective
    0.07
     reversible
    0.07
     intervening
    0.07
    Activations Density 0.010%

    No Known Activations