© 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. 28421
    Prev
    Next
    INDEX
    Explanations

    Re names

    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
    ments
    -0.13
    loc
    -0.12
    mb
    -0.12
    lo
    -0.12
    nt
    -0.11
    med
    -0.11
    ness
    -0.11
    ductive
    -0.11
    li
    -0.11
    ders
    -0.11
    POSITIVE LOGITS
    illy
    0.13
    iko
    0.10
    ibel
    0.09
    building
    0.09
    actions
    0.09
    eder
    0.09
    bec
    0.09
    boot
    0.09
    alo
    0.09
    inh
    0.09
    Activations Density 0.048%

    No Known Activations