© 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. 27886
    Prev
    Next
    INDEX
    Explanations

    yes or no decisions

    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
    oire
    -0.08
     Laure
    -0.08
     auditor
    -0.07
     Hamp
    -0.07
     Mang
    -0.07
     Diy
    -0.06
    ajes
    -0.06
    leur
    -0.06
     deltaX
    -0.06
     Lace
    -0.06
    POSITIVE LOGITS
     —↵↵
    0.11
    linger
    0.11
    pez
    0.10
    iales
    0.10
     massac
    0.10
     ë°ľ
    0.10
    zej
    0.10
     graf
    0.10
    ograd
    0.10
    owie
    0.10
    Activations Density 0.001%

    No Known Activations