© 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. 16303
    Prev
    Next
    INDEX
    Explanations

    mag related words

    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
    ing
    -0.10
    ppo
    -0.09
     Zah
    -0.09
    GRAM
    -0.09
     Gim
    -0.09
     outr
    -0.08
     plat
    -0.08
     grading
    -0.08
    eger
    -0.08
    ìķ¼
    -0.08
    POSITIVE LOGITS
    azine
    0.15
     Mag
    0.15
     mag
    0.14
    ellan
    0.14
    nums
    0.14
    pies
    0.13
    num
    0.13
    icians
    0.13
    cargo
    0.13
    yar
    0.12
    Activations Density 0.040%

    No Known Activations