© 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. 31423
    Prev
    Next
    INDEX
    Explanations

    requirement or mandatory condition

    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
     temptation
    -0.12
     tempting
    -0.11
     Yates
    -0.11
     Cheat
    -0.10
     STDOUT
    -0.10
     cheat
    -0.10
     tempt
    -0.10
     deco
    -0.09
    vari
    -0.09
     consciously
    -0.09
    POSITIVE LOGITS
     requirement
    0.42
     requirements
    0.39
     Requirement
    0.35
     required
    0.34
     Requirements
    0.33
     mandatory
    0.30
     REQUIRE
    0.30
     Required
    0.29
    Requirement
    0.29
     prerequisite
    0.29
    Activations Density 0.687%

    No Known Activations