© 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. 88171
    Prev
    Next
    INDEX
    Explanations

    sending email from

    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
    /email
    -0.13
     EMAIL
    -0.12
    ÃŁe
    -0.12
     Linkedin
    -0.12
     Freeze
    -0.11
     Email
    -0.11
     emailed
    -0.11
     patented
    -0.11
     ($)
    -0.11
     email
    -0.11
    POSITIVE LOGITS
     automated
    0.14
     Automated
    0.11
    bounce
    0.11
     automat
    0.11
     originating
    0.10
     bounce
    0.10
     automatic
    0.10
     automatically
    0.09
     baff
    0.09
     Domain
    0.09
    Activations Density 0.375%

    No Known Activations