© 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. 89850
    Prev
    Next
    INDEX
    Explanations

    non-

    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
    alah
    -0.10
    hti
    -0.08
     Zi
    -0.08
    ivar
    -0.08
     onsite
    -0.07
    ijo
    -0.07
    alta
    -0.07
    otime
    -0.07
     underground
    -0.07
     extremes
    -0.07
    POSITIVE LOGITS
     non
    0.70
    non
    0.59
     Non
    0.58
     NON
    0.57
    Non
    0.54
    (non
    0.53
    -non
    0.52
     unrelated
    0.50
    _non
    0.49
    NON
    0.48
    Activations Density 2.188%

    No Known Activations