© 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. 14371
    Prev
    Next
    INDEX
    Explanations

    storage containers

    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
     Boyle
    -0.10
    orz
    -0.09
    /is
    -0.09
     moto
    -0.09
    alone
    -0.09
     PSG
    -0.09
     COMMIT
    -0.09
     McB
    -0.09
    _DEFAULT
    -0.09
     Meyer
    -0.08
    POSITIVE LOGITS
    æĶ¾
    0.11
    onto
    0.11
     stash
    0.11
    za
    0.10
    cribe
    0.09
    oka
    0.09
    ZA
    0.09
    semb
    0.09
     pocket
    0.09
     amb
    0.09
    Activations Density 0.109%

    No Known Activations