© 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. 30678
    Prev
    Next
    INDEX
    Explanations

    magazine and publication names

    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
     teammate
    -0.09
    åŁ
    -0.09
     invalidate
    -0.09
    seg
    -0.09
     waking
    -0.09
     wake
    -0.08
     Wellington
    -0.08
    ég
    -0.08
    bling
    -0.08
     grind
    -0.08
    POSITIVE LOGITS
     magazine
    0.29
     Magazine
    0.21
     magazines
    0.21
    mag
    0.20
     mag
    0.17
    .mag
    0.15
     subscription
    0.14
     MAG
    0.14
    azine
    0.14
    Mag
    0.13
    Activations Density 0.065%

    No Known Activations