© 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. 18282
    Prev
    Next
    INDEX
    Explanations

    ?

    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
    alic
    -0.12
    -origin
    -0.10
    mond
    -0.10
     seis
    -0.10
    loe
    -0.10
    Elem
    -0.10
     NPR
    -0.09
    092
    -0.09
    faq
    -0.09
    [source
    -0.09
    POSITIVE LOGITS
     Garn
    0.10
     bull
    0.08
     jewish
    0.08
     spont
    0.08
     whit
    0.07
     Ill
    0.07
     sticky
    0.07
     happiest
    0.07
    urat
    0.07
     sacked
    0.07
    Activations Density 0.003%

    No Known Activations