© 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. 17065
    Prev
    Next
    INDEX
    Explanations

    forgotten or swept aside

    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
    sad
    -0.10
     finally
    -0.10
    azi
    -0.10
    opers
    -0.09
    finally
    -0.09
     agony
    -0.09
    .www
    -0.09
    ĵį
    -0.09
    #ac
    -0.09
    296
    -0.09
    POSITIVE LOGITS
     normal
    0.19
     forget
    0.18
     forgetting
    0.18
    normal
    0.17
     chalk
    0.16
     embarrassment
    0.16
     Normal
    0.15
     forgotten
    0.15
     resumed
    0.15
     erased
    0.15
    Activations Density 0.039%

    No Known Activations