© 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. 48635
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    usan
    -0.09
     mailing
    -0.09
     squir
    -0.09
     liter
    -0.08
    atory
    -0.08
    /ion
    -0.08
    errar
    -0.08
     disemb
    -0.08
    âĢ¦
    -0.08
     engineers
    -0.08
    POSITIVE LOGITS
     priced
    0.12
     offerings
    0.12
     catering
    0.12
     hourly
    0.12
     offering
    0.11
     Decl
    0.11
     advert
    0.11
     pricing
    0.11
     profitable
    0.11
     lucrative
    0.11
    Activations Density 0.000%

    No Known Activations