© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 18560
    Prev
    Next
    INDEX
    Explanations

    memories and things to forget

    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
    Negative Logits
     Dimit
    -0.09
    acro
    -0.07
     Except
    -0.07
     Hue
    -0.07
    .Today
    -0.07
     alm
    -0.07
    umni
    -0.07
     retros
    -0.07
     pict
    -0.07
     motivating
    -0.07
    POSITIVE LOGITS
    able
    0.12
     shake
    0.11
     stale
    0.11
     shakes
    0.11
    rick
    0.10
    baar
    0.10
    redi
    0.10
    iquer
    0.10
    amar
    0.10
    textures
    0.10
    Activations Density 0.002%

    No Known Activations