© 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. 31957
    Prev
    Next
    INDEX
    Explanations

    admits, confesses, openly

    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
     Crud
    -0.10
    inic
    -0.10
     courtesy
    -0.10
    idth
    -0.10
    esters
    -0.09
     announcements
    -0.09
     Dome
    -0.09
    ether
    -0.09
    	endif
    -0.09
     reels
    -0.09
    POSITIVE LOGITS
     upfront
    0.14
     openly
    0.14
     wrongdoing
    0.13
     aloud
    0.13
     publicly
    0.12
     freely
    0.12
     readily
    0.11
     reluctantly
    0.11
     admits
    0.10
     sins
    0.10
    Activations Density 0.044%

    No Known Activations