© 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. 17005
    Prev
    Next
    INDEX
    Explanations

    living with

    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
     lives
    -0.10
     sandwich
    -0.08
     foul
    -0.08
     life
    -0.07
     lifespan
    -0.07
    446
    -0.07
     messing
    -0.07
     pimp
    -0.07
     homeland
    -0.07
    usal
    -0.07
    POSITIVE LOGITS
     uncertainty
    0.13
     scars
    0.12
     secrets
    0.11
     roommate
    0.11
     uncertainties
    0.11
     constant
    0.11
    gether
    0.11
     regrets
    0.11
     HIV
    0.11
     chronic
    0.11
    Activations Density 0.047%

    No Known Activations