© 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. 3823
    Prev
    Next
    INDEX
    Explanations

    frozen, ice, and cold temperatures

    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
     faint
    -0.09
     oriented
    -0.09
     smo
    -0.08
     Finite
    -0.08
    abr
    -0.08
    Fully
    -0.08
    çŃ¾
    -0.08
    ations
    -0.08
    vent
    -0.08
     uptake
    -0.08
    POSITIVE LOGITS
     ice
    0.23
     thaw
    0.21
     Ice
    0.20
    Ice
    0.19
     âĿ
    0.18
     icy
    0.18
     Frozen
    0.18
     snow
    0.18
     winters
    0.18
     frost
    0.17
    Activations Density 0.212%

    No Known Activations