© 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. 33055
    Prev
    Next
    INDEX
    Explanations

    holding and possession

    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
     Pall
    -0.13
     Glas
    -0.13
     Mobil
    -0.11
     pall
    -0.11
     fists
    -0.11
     Espresso
    -0.11
     punching
    -0.11
    Coin
    -0.11
    vinc
    -0.11
    plat
    -0.10
    POSITIVE LOGITS
     handed
    0.22
     handing
    0.21
     holding
    0.20
     Holding
    0.19
     holder
    0.17
     toss
    0.16
     Holder
    0.16
     discard
    0.16
     tossed
    0.16
     holders
    0.15
    Activations Density 0.071%

    No Known Activations