© 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. 14741
    Prev
    Next
    INDEX
    Explanations

    freely or unrestricted

    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
     suddenly
    -0.11
     quickly
    -0.09
     somehow
    -0.08
     som
    -0.08
     consistently
    -0.08
     Tight
    -0.07
     hastily
    -0.07
    Abr
    -0.07
     serious
    -0.07
     swiftly
    -0.07
    POSITIVE LOGITS
     freely
    0.45
     unrestricted
    0.32
     unlimited
    0.32
     whichever
    0.27
     anytime
    0.27
     whatever
    0.26
     Unlimited
    0.25
     optionally
    0.22
    whatever
    0.21
     impunity
    0.21
    Activations Density 0.445%

    No Known Activations