© 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. 32193
    Prev
    Next
    INDEX
    Explanations

    free of charge

    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
    paced
    -0.09
     numeric
    -0.09
     Seconds
    -0.09
     severed
    -0.09
     incarcer
    -0.09
    Scoped
    -0.08
     ascend
    -0.08
     Eg
    -0.08
     distancing
    -0.08
     Vers
    -0.08
    POSITIVE LOGITS
     gratis
    0.56
     free
    0.52
     FREE
    0.46
    gratis
    0.42
    free
    0.42
    FREE
    0.40
     unpaid
    0.38
     Free
    0.35
     gratuitement
    0.34
     kostenlos
    0.34
    Activations Density 0.426%

    No Known Activations