© 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. 16164
    Prev
    Next
    INDEX
    Explanations

    do not be mistaken

    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
    agt
    -0.09
     consciously
    -0.09
    ensch
    -0.09
     Stoke
    -0.08
     fend
    -0.08
    stm
    -0.08
    ecz
    -0.08
     WOW
    -0.08
     magically
    -0.08
     gee
    -0.08
    POSITIVE LOGITS
     confuse
    0.19
     forget
    0.19
     worry
    0.19
     underestimate
    0.18
     mistaken
    0.17
     Panic
    0.17
     misunderstand
    0.17
     panic
    0.17
     mistake
    0.16
     misunderstanding
    0.16
    Activations Density 0.105%

    No Known Activations