© 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. 31709
    Prev
    Next
    INDEX
    Explanations

    afropunk.com

    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
     invol
    -0.11
     sama
    -0.10
    flare
    -0.10
     ðŁij
    -0.09
     PREF
    -0.09
     annunci
    -0.09
    variant
    -0.09
     flare
    -0.09
    kop
    -0.09
     Leer
    -0.09
    POSITIVE LOGITS
     lingerie
    0.10
     Winter
    0.09
    feb
    0.09
     gifts
    0.09
     Raz
    0.09
     Supplies
    0.09
    Winter
    0.09
     Feng
    0.09
     Father
    0.08
     Spa
    0.08
    Activations Density 0.001%

    No Known Activations