© 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. 5872
    Prev
    Next
    INDEX
    Explanations

    pontine, pontifical, pontiff, ponte

    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
     pellet
    -0.11
     Crosby
    -0.10
    uite
    -0.10
    rieb
    -0.09
    preload
    -0.08
    flow
    -0.08
    indsay
    -0.08
     discreet
    -0.08
     Rush
    -0.08
    inate
    -0.08
    POSITIVE LOGITS
    Severity
    0.10
    Spo
    0.10
    akin
    0.09
    Spoiler
    0.09
     Attribution
    0.09
     entirety
    0.09
    DRV
    0.09
    magnitude
    0.08
    /reference
    0.08
     posterior
    0.08
    Activations Density 0.002%

    No Known Activations