© 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. 116140
    Prev
    Next
    INDEX
    Explanations

    deadly legends, out incredible, nature., up for, monastery, view of, Time course, effects of

    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
     Attach
    -0.11
    iani
    -0.10
    hin
    -0.09
    atore
    -0.09
     immedi
    -0.09
     Candidate
    -0.09
     embroid
    -0.09
    ché
    -0.09
    emu
    -0.09
     smelled
    -0.09
    POSITIVE LOGITS
     featured
    0.13
     sometimes
    0.13
     often
    0.12
     protagonists
    0.12
     featuring
    0.11
     ranging
    0.11
     either
    0.11
     camer
    0.11
    —from
    0.11
     themselves
    0.11
    Activations Density 0.037%

    No Known Activations