© 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. 30242
    Prev
    Next
    INDEX
    Explanations

    multi / multiple

    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
    arl
    -0.12
    acon
    -0.12
     suff
    -0.11
    tout
    -0.11
     repr
    -0.10
    idth
    -0.10
     alike
    -0.10
     prer
    -0.10
    oup
    -0.10
     twin
    -0.10
    POSITIVE LOGITS
    /single
    0.18
    -multi
    0.15
    -mult
    0.14
    /m
    0.14
     orgas
    0.11
     simultaneous
    0.11
     sclerosis
    0.11
    -single
    0.11
    multi
    0.11
     multi
    0.11
    Activations Density 0.229%

    No Known Activations