© 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. 46545
    Prev
    Next
    INDEX
    Explanations

    slots, casino, viagra, footballer, Bravia

    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
     Pharma
    -0.09
    ctors
    -0.09
    æĤ¨
    -0.08
    ded
    -0.08
     whatever
    -0.08
     Sodium
    -0.08
     blades
    -0.08
    iet
    -0.08
    ave
    -0.08
     Braz
    -0.07
    POSITIVE LOGITS
     Bowen
    0.11
    -inv
    0.09
    ëĭ¹
    0.09
    annah
    0.09
    ertino
    0.08
     composite
    0.08
    roma
    0.08
     Dough
    0.08
     Nz
    0.08
    /network
    0.08
    Activations Density 0.040%

    No Known Activations