© 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. 91153
    Prev
    Next
    INDEX
    Explanations

    enjoys sucking

    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
     afterward
    -0.11
     initiating
    -0.09
    ients
    -0.09
     subsequently
    -0.09
    Bru
    -0.09
    DEX
    -0.09
     incapac
    -0.09
     thereafter
    -0.08
     advert
    -0.08
     hormone
    -0.08
    POSITIVE LOGITS
     currently
    0.13
    æŃ£åľ¨
    0.12
     bare
    0.11
     monoc
    0.11
    currently
    0.10
     Currently
    0.10
     seated
    0.10
     sucking
    0.10
     tied
    0.10
     steadily
    0.10
    Activations Density 0.034%

    No Known Activations