© 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. 50228
    Prev
    Next
    INDEX
    Explanations

    productions and media

    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
     temporarily
    -0.10
     rehears
    -0.09
     rer
    -0.09
     smack
    -0.09
     unintention
    -0.09
    cono
    -0.09
    poster
    -0.08
    overn
    -0.08
    orp
    -0.08
     spontaneously
    -0.08
    POSITIVE LOGITS
     including
    0.17
     notably
    0.16
     Including
    0.15
     earning
    0.15
    including
    0.14
    earned
    0.13
     throughout
    0.13
     beginning
    0.13
     earned
    0.12
     INCLUDING
    0.12
    Activations Density 2.004%

    No Known Activations