© 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. 48059
    Prev
    Next
    INDEX
    Explanations

    photographed, kissed, composer, software, resume

    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
     drag
    -0.11
    dur
    -0.10
     inward
    -0.10
    vang
    -0.09
    olin
    -0.09
     fren
    -0.09
     dur
    -0.08
     pornography
    -0.08
     porn
    -0.08
     Drag
    -0.08
    POSITIVE LOGITS
    iek
    0.12
     forehead
    0.11
    inkle
    0.10
    roof
    0.10
     bridal
    0.10
     tender
    0.10
     hair
    0.09
    redd
    0.09
     scalp
    0.09
     frag
    0.09
    Activations Density 0.012%

    No Known Activations