© 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. 30889
    Prev
    Next
    INDEX
    Explanations

    rights, license, use, duration, terms

    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
     Chapman
    -0.11
     selfish
    -0.11
    ilton
    -0.10
     illegally
    -0.10
     Unauthorized
    -0.10
     unauthorized
    -0.10
     Gerr
    -0.10
     Cin
    -0.10
    erg
    -0.10
     alert
    -0.10
    POSITIVE LOGITS
     perpetual
    0.12
     indefinite
    0.12
     Roy
    0.11
     perpet
    0.11
    Roy
    0.11
     forever
    0.10
     worldwide
    0.10
     Forever
    0.10
    ellt
    0.09
     Kab
    0.09
    Activations Density 0.092%

    No Known Activations