© 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. 27033
    Prev
    Next
    INDEX
    Explanations

    numbers and special characters

    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
     friendship
    -0.11
     MAC
    -0.10
    MAC
    -0.09
     mandatory
    -0.09
     statutory
    -0.09
     BAM
    -0.09
     parenting
    -0.09
    ampo
    -0.09
     administrative
    -0.09
     promptly
    -0.09
    POSITIVE LOGITS
     Frid
    0.10
     jav
    0.09
     Phill
    0.09
    IPPING
    0.09
    YLES
    0.09
     Burk
    0.09
     incest
    0.08
     ðŁĶ
    0.08
    mos
    0.08
    immel
    0.08
    Activations Density 0.102%

    No Known Activations