© 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. 30693
    Prev
    Next
    INDEX
    Explanations

    RSS feed

    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
    ambi
    -0.11
    ania
    -0.11
     dearly
    -0.10
    uD
    -0.10
    QC
    -0.10
    beg
    -0.10
    ena
    -0.10
    ENO
    -0.10
    abant
    -0.10
     Registr
    -0.10
    POSITIVE LOGITS
    avi
    0.11
     Sof
    0.09
    rev
    0.08
     Zub
    0.08
    osphere
    0.07
     overall
    0.07
     rep
    0.07
     revolt
    0.07
    Bold
    0.07
     Flor
    0.06
    Activations Density 0.007%

    No Known Activations