© 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. 112070
    Prev
    Next
    INDEX
    Explanations

    female subject with intense emotions

    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
     enforcing
    -0.10
     Supern
    -0.10
     Glam
    -0.10
     enforcement
    -0.10
     handsome
    -0.10
     steril
    -0.09
     enforce
    -0.09
     woo
    -0.09
    rott
    -0.09
     celebrity
    -0.09
    POSITIVE LOGITS
     innocence
    0.21
     innocent
    0.17
     Innoc
    0.15
     innoc
    0.14
     purity
    0.13
     defiance
    0.12
     timid
    0.12
     tempting
    0.12
     blush
    0.12
     tempt
    0.12
    Activations Density 0.019%

    No Known Activations