© 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. 50018
    Prev
    Next
    INDEX
    Explanations

    quantities of things or sharing

    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
    enate
    -0.11
     convo
    -0.10
     aup
    -0.10
    oho
    -0.10
    xxxxxxxx
    -0.10
     Sahara
    -0.09
    uges
    -0.09
     "-";↵
    -0.09
     Ah
    -0.09
     âĸĪâĸĪâĸĪâĸĪâĸĪ
    -0.09
    POSITIVE LOGITS
    essen
    0.11
     cross
    0.09
     Ross
    0.09
     Cros
    0.09
    ross
    0.08
    odos
    0.08
    owl
    0.08
     Bron
    0.08
     inspiring
    0.08
     colony
    0.08
    Activations Density 0.001%

    No Known Activations