© 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. 4591
    Prev
    Next
    INDEX
    Explanations

    referred to as

    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
    prt
    -0.10
     repet
    -0.09
     abuses
    -0.09
     everlasting
    -0.09
     repeating
    -0.09
    474
    -0.09
     repetitions
    -0.09
     multiplic
    -0.09
     Persona
    -0.08
     endlessly
    -0.08
    POSITIVE LOGITS
     helicopt
    0.10
     brink
    0.10
     gearing
    0.10
     surfing
    0.09
     capac
    0.09
     vide
    0.09
     retrofit
    0.09
     siden
    0.09
     batching
    0.09
    HEMA
    0.08
    Activations Density 0.742%

    No Known Activations