© 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. 49014
    Prev
    Next
    INDEX
    Explanations

    obedient or do what please

    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
     bluff
    -0.09
    /control
    -0.08
    etti
    -0.08
    Characteristic
    -0.08
     selectively
    -0.08
     selective
    -0.08
     Yan
    -0.08
     incor
    -0.08
     Eaton
    -0.08
     clip
    -0.08
    POSITIVE LOGITS
     tribute
    0.19
     worship
    0.19
     obedient
    0.18
     obedience
    0.16
     serv
    0.15
     obey
    0.15
     pleasing
    0.14
     Worship
    0.14
     servicing
    0.14
     indebted
    0.14
    Activations Density 0.076%

    No Known Activations