© 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. 89854
    Prev
    Next
    INDEX
    Explanations

    film titles, code, or portuguese words

    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
     nons
    -0.10
     steward
    -0.10
     Phrase
    -0.09
     penetr
    -0.09
     Claud
    -0.09
    rok
    -0.09
     cram
    -0.08
     ob
    -0.08
    temps
    -0.08
     stal
    -0.08
    POSITIVE LOGITS
    werk
    0.09
    eneral
    0.09
    opsis
    0.09
    pron
    0.08
     Artifact
    0.08
    adx
    0.08
     alas
    0.08
     chalk
    0.08
     creep
    0.08
    clave
    0.08
    Activations Density 0.314%

    No Known Activations