© 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. 114243
    Prev
    Next
    INDEX
    Explanations

    Mall or Pal variants

    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
    ej
    -0.10
    quia
    -0.10
    quan
    -0.09
    orate
    -0.09
    ffa
    -0.09
    ration
    -0.09
    ker
    -0.09
     Hale
    -0.09
     Nass
    -0.09
     obsess
    -0.09
    POSITIVE LOGITS
    ulu
    0.09
     gy
    0.09
    agnar
    0.09
     Flake
    0.09
     Powered
    0.09
     Emoji
    0.09
    opr
    0.09
     Lucky
    0.09
     Persistent
    0.08
    ahoo
    0.08
    Activations Density 0.005%

    No Known Activations