© 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. 5630
    Prev
    Next
    INDEX
    Explanations

    your erection, her brand, my source

    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
    zell
    -0.10
    jar
    -0.09
     tur
    -0.08
     Duty
    -0.08
     bucket
    -0.08
    ipel
    -0.08
     pouch
    -0.08
     behaving
    -0.08
     cape
    -0.08
     coupe
    -0.08
    POSITIVE LOGITS
     circumference
    0.10
     entirety
    0.10
    ushi
    0.10
     tip
    0.10
     entire
    0.10
     trim
    0.09
     uncomment
    0.09
    ulan
    0.09
    nik
    0.09
    nika
    0.09
    Activations Density 0.006%

    No Known Activations