© 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. 88743
    Prev
    Next
    INDEX
    Explanations

    version 3

    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
    kowski
    -0.12
     Vend
    -0.10
     prop
    -0.10
     Hamp
    -0.10
    erb
    -0.10
     Sov
    -0.10
    gars
    -0.10
    eus
    -0.10
     dancing
    -0.09
     KD
    -0.09
    POSITIVE LOGITS
     gaz
    0.09
     effectively
    0.08
    NOW
    0.08
    éļ
    0.08
     Foot
    0.08
     mam
    0.08
     im
    0.07
     indebted
    0.07
     Growth
    0.07
     runoff
    0.07
    Activations Density 0.001%

    No Known Activations