© 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. 28268
    Prev
    Next
    INDEX
    Explanations

    exactly for this

    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
     deactivate
    -0.10
     dello
    -0.10
    ivent
    -0.10
    anh
    -0.09
     sint
    -0.09
    etta
    -0.09
    URA
    -0.09
    XT
    -0.09
     brutally
    -0.09
    lee
    -0.09
    POSITIVE LOGITS
     precisely
    0.20
     anticipated
    0.19
     emergencies
    0.19
     exactly
    0.17
     specifically
    0.17
     occasions
    0.16
     occasion
    0.14
     Exactly
    0.13
     situations
    0.12
     expected
    0.12
    Activations Density 0.054%

    No Known Activations