© 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. 29387
    Prev
    Next
    INDEX
    Explanations

    reproduction precautions

    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
     Sexual
    -0.12
    bond
    -0.11
     Psychological
    -0.10
     compliment
    -0.10
     Hitch
    -0.10
     Hanson
    -0.10
     Mental
    -0.10
     sexual
    -0.10
     dign
    -0.10
     Webcam
    -0.10
    POSITIVE LOGITS
     unprotected
    0.24
     fertile
    0.17
     ov
    0.14
     irresponsible
    0.13
     careless
    0.12
     contraception
    0.12
     sperm
    0.12
     protection
    0.11
     precautions
    0.11
     gam
    0.11
    Activations Density 0.046%

    No Known Activations