© 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. 17403
    Prev
    Next
    INDEX
    Explanations

    telling you how

    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
     arrog
    -0.09
     Bib
    -0.09
     presumably
    -0.09
     selfish
    -0.09
    olls
    -0.09
    credited
    -0.09
     ceremon
    -0.09
     sno
    -0.08
     credited
    -0.08
    CLE
    -0.08
    POSITIVE LOGITS
     dwarf
    0.10
    iten
    0.09
     surviv
    0.09
    quina
    0.09
     teaches
    0.09
     Conway
    0.09
     zeigen
    0.09
     outs
    0.09
     wiping
    0.09
     #@
    0.09
    Activations Density 0.026%

    No Known Activations