© 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. 6204
    Prev
    Next
    INDEX
    Explanations

    droplets or dots

    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
     shove
    -0.10
     Pist
    -0.10
    whelming
    -0.09
    assin
    -0.09
    OI
    -0.09
    sci
    -0.09
     inh
    -0.09
    INAL
    -0.09
    igin
    -0.09
     academics
    -0.09
    POSITIVE LOGITS
     bead
    0.14
     beads
    0.12
     dro
    0.12
     dots
    0.12
     Dot
    0.12
     dot
    0.11
     sweat
    0.11
     Dro
    0.11
     pearls
    0.11
     cond
    0.11
    Activations Density 0.006%

    No Known Activations