© 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. 88132
    Prev
    Next
    INDEX
    Explanations

    grabbing or holding something

    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
     Budd
    -0.10
     Freddie
    -0.09
     Wilde
    -0.09
    igne
    -0.09
    umo
    -0.09
    etty
    -0.09
     compliment
    -0.08
     tact
    -0.08
     mut
    -0.08
     Hive
    -0.08
    POSITIVE LOGITS
     handles
    0.21
     handle
    0.20
     grips
    0.20
     collar
    0.20
     grab
    0.20
     grabbing
    0.19
    handles
    0.19
     reins
    0.19
     hair
    0.19
     grip
    0.18
    Activations Density 0.170%

    No Known Activations