© 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. 5822
    Prev
    Next
    INDEX
    Explanations

    erectile dysfunction

    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
    eler
    -0.12
    agh
    -0.10
    way
    -0.10
    ela
    -0.10
     Mim
    -0.10
    igar
    -0.09
    erge
    -0.09
    .cam
    -0.09
     nar
    -0.09
     mari
    -0.09
    POSITIVE LOGITS
     dysfunction
    0.13
     problems
    0.11
     strength
    0.11
     Dysfunction
    0.11
     pads
    0.10
     medic
    0.10
    andel
    0.10
    iesel
    0.10
     pad
    0.10
    afone
    0.10
    Activations Density 0.018%

    No Known Activations