© 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. 31403
    Prev
    Next
    INDEX
    Explanations

    online drugs and purchases

    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
     Dumpster
    -0.09
     scrap
    -0.09
     detox
    -0.09
     Lust
    -0.09
     hob
    -0.08
     Socialist
    -0.08
    aeda
    -0.08
    patial
    -0.08
    elib
    -0.08
    -Encoding
    -0.08
    POSITIVE LOGITS
     overnight
    0.15
     legitimate
    0.15
     Overnight
    0.14
     reputable
    0.13
     PayPal
    0.13
     legit
    0.12
     Paypal
    0.12
     shipped
    0.12
     shady
    0.12
     paypal
    0.12
    Activations Density 0.024%

    No Known Activations