© 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. 89498
    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
     Shelter
    -0.11
     Dial
    -0.10
     horm
    -0.10
    soc
    -0.10
    playlist
    -0.10
     Consortium
    -0.10
    junction
    -0.09
    eed
    -0.09
    Pinterest
    -0.09
    avax
    -0.09
    POSITIVE LOGITS
     magician
    0.33
     tricks
    0.26
     illusion
    0.24
     illusions
    0.23
     trick
    0.22
     magic
    0.22
     Tricks
    0.21
     performer
    0.20
     MAGIC
    0.19
     mag
    0.19
    Activations Density 0.176%

    No Known Activations