© 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. 33691
    Prev
    Next
    INDEX
    Explanations

    eliminating altogether

    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
    instead
    -0.10
     apl
    -0.09
     uncont
    -0.09
     hoop
    -0.09
     gam
    -0.09
     closely
    -0.09
    oucher
    -0.09
     instead
    -0.08
     Dia
    -0.08
    ennie
    -0.08
    POSITIVE LOGITS
     altogether
    0.37
     permanently
    0.29
    alto
    0.29
     completely
    0.27
     entirely
    0.26
     Alto
    0.25
     forever
    0.24
     abruptly
    0.23
     Completely
    0.22
     temporarily
    0.20
    Activations Density 0.621%

    No Known Activations