© 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. 114964
    Prev
    Next
    INDEX
    Explanations

    slit, slice, aperture, sequences, permissions

    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
    een
    -0.11
    lest
    -0.11
    anine
    -0.11
    s
    -0.11
    eer
    -0.10
    hoot
    -0.10
     litt
    -0.10
    inges
    -0.10
     pied
    -0.10
    bras
    -0.10
    POSITIVE LOGITS
    ELY
    0.09
    omic
    0.09
     Hof
    0.09
    NEY
    0.08
    blick
    0.08
     lining
    0.08
    better
    0.08
    -up
    0.08
     cre
    0.08
    åı£
    0.07
    Activations Density 0.001%

    No Known Activations