© 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. 7914
    Prev
    Next
    INDEX
    Explanations

    un / un-

    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
    Da
    -0.11
    ito
    -0.11
     Platt
    -0.10
     Da
    -0.10
    обÑĢаÐ
    -0.10
     hops
    -0.09
    loser
    -0.09
    aan
    -0.09
     Hind
    -0.09
     Diamond
    -0.09
    POSITIVE LOGITS
     roy
    0.10
    /re
    0.10
     congest
    0.09
    /address
    0.09
    uction
    0.09
    vir
    0.09
     muddy
    0.08
    /up
    0.08
     pseud
    0.08
     bunk
    0.08
    Activations Density 0.080%

    No Known Activations