© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 92505
    Prev
    Next
    INDEX
    Explanations

    communication channels (text, fax, email, slack)

    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
    Negative Logits
    subs
    -0.10
    resher
    -0.10
     consciously
    -0.10
     grounding
    -0.10
     Aff
    -0.10
    aine
    -0.10
     oral
    -0.10
    ë¦Ħ
    -0.09
     Dia
    -0.09
     sof
    -0.09
    POSITIVE LOGITS
     chat
    0.09
    /email
    0.09
    chat
    0.08
     Marketing
    0.08
    -chat
    0.08
     Gor
    0.08
     candid
    0.08
     Bot
    0.07
     chats
    0.07
    :+
    0.07
    Activations Density 0.014%

    No Known Activations