© 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. 48167
    Prev
    Next
    INDEX
    Explanations

    memoir and personal recount

    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
    oti
    -0.11
    zyst
    -0.10
    plier
    -0.10
     Characters
    -0.10
    åķĨ
    -0.10
     disagreement
    -0.10
     Kul
    -0.10
     eternal
    -0.10
    unteers
    -0.10
     playable
    -0.09
    POSITIVE LOGITS
     memoir
    0.37
     autobi
    0.33
     autobiography
    0.30
     experiences
    0.29
     diary
    0.26
     Memo
    0.25
     recount
    0.23
     Diary
    0.22
    memo
    0.22
    Memo
    0.22
    Activations Density 0.301%

    No Known Activations