© 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. 16520
    Prev
    Next
    INDEX
    Explanations

    helmets and wheel covers

    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
     thrust
    -0.09
     kre
    -0.09
     Klan
    -0.09
     ker
    -0.08
    utral
    -0.08
     Tone
    -0.08
     NOTICE
    -0.08
     nto
    -0.08
    -san
    -0.08
    781
    -0.08
    POSITIVE LOGITS
     Bag
    0.10
    ouched
    0.10
     temper
    0.10
     Mellon
    0.10
     vacancy
    0.10
     searchable
    0.10
     yoga
    0.09
    atte
    0.09
     unreachable
    0.09
     cris
    0.09
    Activations Density 0.001%

    No Known Activations