© 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. 114703
    Prev
    Next
    INDEX
    Explanations

    ashes and dust

    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
     wrest
    -0.11
    aria
    -0.11
     Cutting
    -0.10
     cutting
    -0.10
     flipped
    -0.09
     Sau
    -0.09
     inverted
    -0.09
    untu
    -0.09
     Pend
    -0.09
    eds
    -0.09
    POSITIVE LOGITS
     ashes
    0.20
     dissolve
    0.19
     dissolved
    0.19
     dust
    0.18
     dispersed
    0.17
     vapor
    0.17
     dissolution
    0.17
     diss
    0.16
     ash
    0.15
     dissip
    0.15
    Activations Density 0.234%

    No Known Activations