© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 113681
    Prev
    Next
    INDEX
    Explanations

    That depends

    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
    alis
    -0.09
     Plenty
    -0.09
     coolest
    -0.09
    yang
    -0.09
     retros
    -0.09
    955
    -0.08
     Yep
    -0.08
     lots
    -0.08
     Nope
    -0.08
     op
    -0.08
    POSITIVE LOGITS
     depends
    0.14
     depend
    0.13
     Depends
    0.12
    depends
    0.12
     depended
    0.11
     remark
    0.10
    depend
    0.10
    omen
    0.10
     surprises
    0.10
    gis
    0.09
    Activations Density 0.041%

    No Known Activations