© 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. 116157
    Prev
    Next
    INDEX
    Explanations

    slave or prisoner status

    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
     ensl
    -0.11
     enslaved
    -0.11
     Membership
    -0.09
     subordinate
    -0.09
     membership
    -0.09
     memberships
    -0.08
    Membership
    -0.08
     dict
    -0.08
     indent
    -0.08
     serv
    -0.08
    POSITIVE LOGITS
    oth
    0.13
     Sel
    0.11
     bil
    0.11
     meteor
    0.10
     Apprec
    0.10
     TRADE
    0.10
    pty
    0.10
    ylan
    0.10
     Gee
    0.10
     comb
    0.10
    Activations Density 0.032%

    No Known Activations