© 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. 28514
    Prev
    Next
    INDEX
    Explanations

    nonsensical claims

    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
     oppon
    -0.10
     sober
    -0.10
     genu
    -0.09
     legitimately
    -0.09
    omal
    -0.09
    anova
    -0.09
    wer
    -0.09
     ugl
    -0.09
    ãģĹãģĭ
    -0.09
     accidentally
    -0.09
    POSITIVE LOGITS
     nonsense
    0.31
     ridiculous
    0.26
     incorrect
    0.25
     unnecessary
    0.25
     silly
    0.24
     misguided
    0.24
     wrong
    0.24
     unrealistic
    0.23
     absurd
    0.23
     false
    0.22
    Activations Density 0.322%

    No Known Activations