© 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. 31815
    Prev
    Next
    INDEX
    Explanations

    possibility and uncertainty

    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
     undoubtedly
    -0.11
     unquestion
    -0.11
    coli
    -0.11
     obviously
    -0.11
     Unauthorized
    -0.11
     toast
    -0.10
     conspic
    -0.10
    vor
    -0.10
    agine
    -0.10
    (strict
    -0.10
    POSITIVE LOGITS
     soon
    0.11
     tomorrow
    0.10
     someday
    0.10
     somewhere
    0.09
    will
    0.08
    ä¼ļ
    0.08
    .Maybe
    0.08
    -m
    0.08
    Will
    0.08
     Inst
    0.08
    Activations Density 0.031%

    No Known Activations