© 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. 115199
    Prev
    Next
    INDEX
    Explanations

    do something

    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
    eken
    -0.10
     flea
    -0.08
     Falk
    -0.08
     cla
    -0.08
     Vent
    -0.08
     Zeit
    -0.08
    uk
    -0.08
    inned
    -0.08
    pon
    -0.08
    cke
    -0.08
    POSITIVE LOGITS
    ORMAT
    0.10
     Dane
    0.10
    .uf
    0.10
     amat
    0.09
     Maze
    0.09
    dale
    0.09
     edm
    0.09
    íĻĺ
    0.09
    abilité
    0.09
     suce
    0.09
    Activations Density 0.050%

    No Known Activations