© 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. 114573
    Prev
    Next
    INDEX
    Explanations

    July or summer months

    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
     winter
    -0.12
     winters
    -0.12
     Winter
    -0.11
     snowy
    -0.10
    Winter
    -0.10
    iti
    -0.10
    al
    -0.09
     Christmas
    -0.08
     January
    -0.08
     scoped
    -0.08
    POSITIVE LOGITS
    -Aug
    0.16
    aines
    0.13
    summer
    0.13
    July
    0.13
     summer
    0.13
     July
    0.13
     Aug
    0.13
    份
    0.13
     AUG
    0.12
     augmented
    0.12
    Activations Density 0.161%

    No Known Activations