© 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. 116936
    Prev
    Next
    INDEX
    Explanations

    possessive pronouns followed by body parts

    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
    umbn
    -0.10
     kino
    -0.09
     Sans
    -0.09
     âŀ
    -0.09
     ank
    -0.09
     McConnell
    -0.09
     cuffs
    -0.09
    xDE
    -0.09
     spare
    -0.09
     pools
    -0.09
    POSITIVE LOGITS
     scor
    0.11
     distra
    0.09
     abused
    0.09
     wounded
    0.09
     briefly
    0.08
    ìĭł
    0.08
     disturbed
    0.08
     misc
    0.08
     stirring
    0.08
     served
    0.08
    Activations Density 0.028%

    No Known Activations