© 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. 27078
    Prev
    Next
    INDEX
    Explanations

    without warranties or conditions

    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
     vet
    -0.10
    ptom
    -0.10
     reopen
    -0.09
    cki
    -0.09
    psy
    -0.09
    iable
    -0.09
    uzzer
    -0.09
    rez
    -0.09
     Observatory
    -0.09
     Sch
    -0.08
    POSITIVE LOGITS
     gratuit
    0.10
    ór
    0.09
    ind
    0.09
    iner
    0.09
     Tut
    0.09
    /cgi
    0.09
     Trace
    0.09
    iven
    0.09
    LO
    0.09
     complic
    0.09
    Activations Density 0.023%

    No Known Activations