© 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. 17355
    Prev
    Next
    INDEX
    Explanations

    sun exposure

    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
     Sug
    -0.09
    jen
    -0.09
     serr
    -0.08
     Meer
    -0.08
     Engines
    -0.08
    åĮ
    -0.08
     Blanco
    -0.08
     sug
    -0.08
     Nationwide
    -0.08
    156
    -0.07
    POSITIVE LOGITS
    ken
    0.16
     Microsystems
    0.15
    flower
    0.15
    spots
    0.14
    shine
    0.13
     âĺ
    0.13
    nah
    0.13
    niest
    0.13
    roof
    0.13
    flowers
    0.13
    Activations Density 0.133%

    No Known Activations