© 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. 117159
    Prev
    Next
    INDEX
    Explanations

    may differ, it's like

    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
     suffer
    -0.10
     Kun
    -0.09
     sk
    -0.09
     Pound
    -0.09
     suffers
    -0.09
    äl
    -0.09
     happy
    -0.09
    bling
    -0.09
     visible
    -0.09
     suffered
    -0.09
    POSITIVE LOGITS
    usher
    0.12
     Spicer
    0.10
     restr
    0.09
     Weiner
    0.09
     Glam
    0.09
     Rede
    0.09
     sensation
    0.09
    chan
    0.09
     exper
    0.08
     paran
    0.08
    Activations Density 0.009%

    No Known Activations