© 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. 88385
    Prev
    Next
    INDEX
    Explanations

    extinction, mystery, absent; planet, mammals

    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
     Caj
    -0.09
    esk
    -0.09
     eastern
    -0.09
     earliest
    -0.08
     proto
    -0.08
    Asian
    -0.08
     Eastern
    -0.08
    /constants
    -0.08
     Hatch
    -0.08
     wag
    -0.08
    POSITIVE LOGITS
     planet
    0.11
    utas
    0.11
    nos
    0.11
     mammals
    0.10
    uta
    0.10
     mamma
    0.10
    /pr
    0.10
     bl
    0.10
     Relative
    0.10
    aho
    0.10
    Activations Density 0.118%

    No Known Activations