© 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. 49397
    Prev
    Next
    INDEX
    Explanations

    giving consent or agreeing

    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
     Hawks
    -0.11
    -exc
    -0.10
     doubling
    -0.09
    mach
    -0.09
     Exc
    -0.08
     Hath
    -0.08
    alf
    -0.08
     doubled
    -0.08
     priesthood
    -0.08
     Doub
    -0.08
    POSITIVE LOGITS
     signifies
    0.13
     consenting
    0.12
     consent
    0.12
     agrees
    0.11
     indicates
    0.11
     implies
    0.11
     agree
    0.11
     affirm
    0.11
     signify
    0.11
     YOU
    0.11
    Activations Density 0.041%

    No Known Activations