© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 48802
    Prev
    Next
    INDEX
    Explanations

    forgotten or remembering

    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
    hecy
    -0.09
     Genuine
    -0.08
     Cole
    -0.08
     capital
    -0.08
     unsupported
    -0.08
    ITT
    -0.08
     unsub
    -0.08
     suffice
    -0.08
    Capital
    -0.08
     genuine
    -0.07
    POSITIVE LOGITS
     forgotten
    0.16
     forgetting
    0.16
     deaf
    0.15
     forget
    0.15
     forgot
    0.15
     WANT
    0.14
    forgot
    0.12
     think
    0.11
     Forgot
    0.11
     recall
    0.11
    Activations Density 0.047%

    No Known Activations