© 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. 116590
    Prev
    Next
    INDEX
    Explanations

    remembering, recalling, forgetting

    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
     Mime
    -0.11
    isko
    -0.09
     dram
    -0.09
    ...,
    -0.09
     Mixer
    -0.09
    avian
    -0.09
    ormsg
    -0.09
     praises
    -0.08
    scheme
    -0.08
     OE
    -0.08
    POSITIVE LOGITS
     remember
    0.16
     Remember
    0.14
     remembering
    0.13
    recall
    0.13
    Remember
    0.13
    remember
    0.13
     forgetting
    0.13
     forget
    0.12
     remembers
    0.12
     that
    0.12
    Activations Density 0.039%

    No Known Activations