© 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. 32007
    Prev
    Next
    INDEX
    Explanations

    hell or shit

    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
    eny
    -0.12
     Bez
    -0.10
     convincing
    -0.10
    nger
    -0.09
     zer
    -0.09
    beck
    -0.09
     Engel
    -0.09
     reco
    -0.09
     Herz
    -0.09
     tame
    -0.09
    POSITIVE LOGITS
     hell
    0.49
     heck
    0.45
     Hell
    0.32
    hell
    0.31
    Hell
    0.28
     Heck
    0.27
     shit
    0.23
     crap
    0.21
    heck
    0.21
    HELL
    0.21
    Activations Density 0.140%

    No Known Activations