© 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. 30774
    Prev
    Next
    INDEX
    Explanations

    unknown or impossible

    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
    aret
    -0.12
    olio
    -0.10
    -ui
    -0.10
     aur
    -0.10
     Prel
    -0.10
    inia
    -0.10
     HOL
    -0.10
     Vall
    -0.09
    Camb
    -0.09
    ampler
    -0.09
    POSITIVE LOGITS
     unknow
    0.24
     forever
    0.23
     never
    0.19
     impossible
    0.17
     Forever
    0.16
     unknown
    0.16
     Never
    0.15
     imposs
    0.15
    never
    0.15
     Impossible
    0.14
    Activations Density 0.139%

    No Known Activations