© 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. 30210
    Prev
    Next
    INDEX
    Explanations

    completely, fully, wholeheartedly

    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
    /sources
    -0.09
    -debug
    -0.09
    asan
    -0.09
    aiser
    -0.09
    /AFP
    -0.09
    itant
    -0.09
    ëĭ¹
    -0.09
     ingenious
    -0.09
     carefully
    -0.09
    gle
    -0.09
    POSITIVE LOGITS
     fully
    0.34
     completely
    0.30
     Fully
    0.29
     Completely
    0.26
     FULL
    0.24
     unrestricted
    0.24
     fullest
    0.24
     wholly
    0.24
    Fully
    0.24
     totally
    0.21
    Activations Density 0.051%

    No Known Activations