© 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. 112762
    Prev
    Next
    INDEX
    Explanations

    email opt-in and subscription management

    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
     Bri
    -0.09
    ELS
    -0.09
     bureaucr
    -0.09
     repost
    -0.08
     flush
    -0.08
     flushed
    -0.08
     Parm
    -0.08
     banker
    -0.08
    coni
    -0.08
     Trit
    -0.08
    POSITIVE LOGITS
     unsubscribe
    0.20
    unsubscribe
    0.17
     opt
    0.17
     spam
    0.14
     opting
    0.13
     vow
    0.13
    spam
    0.12
     newsletters
    0.12
    .subscribe
    0.12
     subscriptions
    0.12
    Activations Density 0.030%

    No Known Activations