© 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. 114874
    Prev
    Next
    INDEX
    Explanations

    magic tricks

    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
     fit
    -0.10
    .Import
    -0.09
     Fuse
    -0.09
     clash
    -0.09
     diver
    -0.09
    rees
    -0.09
     divergence
    -0.09
    HIR
    -0.09
     stalk
    -0.09
     furn
    -0.09
    POSITIVE LOGITS
     tricks
    0.37
     Tricks
    0.32
     trick
    0.32
     Trick
    0.28
     tricky
    0.20
     deceive
    0.17
     dece
    0.17
     fooled
    0.17
     deceit
    0.14
     prank
    0.14
    Activations Density 0.040%

    No Known Activations