© 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. 7332
    Prev
    Next
    INDEX
    Explanations

    actions ending in ing

    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
    ings
    -0.16
    ing
    -0.12
    INGS
    -0.11
    ING
    -0.11
    ingly
    -0.09
    ÂŃing
    -0.09
    icing
    -0.09
    ling
    -0.08
    inge
    -0.08
    onal
    -0.08
    POSITIVE LOGITS
     done
    0.14
     prowess
    0.14
     behavior
    0.13
     spree
    0.13
    est
    0.12
     habits
    0.12
     sessions
    0.12
    done
    0.11
     Done
    0.11
     Gunn
    0.11
    Activations Density 0.502%

    No Known Activations