© 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. 90018
    Prev
    Next
    INDEX
    Explanations

    command line, GD FileManager, rule service

    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
     #-
    -0.09
     {_
    -0.08
    .lv
    -0.08
    rix
    -0.08
     —↵↵
    -0.08
     melod
    -0.08
    Charset
    -0.08
     bm
    -0.08
    ense
    -0.08
    (KP
    -0.08
    POSITIVE LOGITS
    velt
    0.09
     sunk
    0.09
     insult
    0.09
    tant
    0.08
    indow
    0.08
    -know
    0.08
    776
    0.08
     insults
    0.07
    emean
    0.07
    acl
    0.07
    Activations Density 1.051%

    No Known Activations