© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 27462
    Prev
    Next
    INDEX
    Explanations

    online forums

    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
    osten
    -0.11
    eren
    -0.10
    иÑĩеÑģ
    -0.10
    OI
    -0.10
    avo
    -0.10
    estr
    -0.10
    /original
    -0.10
    imenti
    -0.09
     fick
    -0.09
    nger
    -0.09
    POSITIVE LOGITS
     moderated
    0.10
    warz
    0.10
    otion
    0.09
    .sleep
    0.09
     ras
    0.09
     moderation
    0.09
    iston
    0.09
     frequ
    0.09
    /chat
    0.09
     Moderator
    0.08
    Activations Density 0.016%

    No Known Activations