© 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
    2. Olmo-3-1125-32B
    3. 32-RES-BATCHTOPK-131K
    4. 46708
    Prev
    Next
    INDEX
    Explanations

    shower upon, rain of, display of

    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
     Scre
    -0.09
     standby
    -0.09
    indi
    -0.09
     lurking
    -0.08
     prow
    -0.08
    orang
    -0.08
    inder
    -0.08
    gre
    -0.08
     Kes
    -0.08
    INDER
    -0.08
    POSITIVE LOGITS
     shower
    0.15
     praise
    0.13
     upon
    0.13
     praises
    0.13
     gifts
    0.13
     blessings
    0.13
     lav
    0.13
     showers
    0.13
     affection
    0.12
     Shower
    0.12
    Activations Density 0.013%

    No Known Activations