© 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. 48742
    Prev
    Next
    INDEX
    Explanations

    Guimar Portuguese names

    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
     Pant
    -0.08
    .misc
    -0.08
    /ion
    -0.07
    Misc
    -0.07
    STAT
    -0.07
     {\
    -0.07
     atmos
    -0.07
     Giants
    -0.06
    /part
    -0.06
     stat
    -0.06
    POSITIVE LOGITS
     normalized
    0.10
    ÑĤе
    0.10
    undo
    0.10
     drip
    0.09
    orate
    0.09
     Mane
    0.09
    /DTD
    0.09
    quiv
    0.09
    amble
    0.09
    elier
    0.09
    Activations Density 0.099%

    No Known Activations