© 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. 114972
    Prev
    Next
    INDEX
    Explanations

    "ÃĤ" or non-standard characters

    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
     Deutsch
    -0.10
    ÈĽi
    -0.09
    apis
    -0.09
     Wagner
    -0.09
    licht
    -0.09
     Klaus
    -0.09
     replicate
    -0.09
    ews
    -0.09
     cul
    -0.09
     Perf
    -0.09
    POSITIVE LOGITS
    es
    0.11
    s
    0.11
    iom
    0.09
    alia
    0.08
    Âł↵
    0.08
    aines
    0.08
    rite
    0.08
    aad
    0.07
     genesis
    0.07
     customary
    0.07
    Activations Density 0.004%

    No Known Activations