© 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. 30318
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    äºİ
    -0.10
     Amar
    -0.10
     counterfeit
    -0.10
    ampo
    -0.10
     pri
    -0.10
    umps
    -0.10
     CBC
    -0.10
     Stard
    -0.10
    /lic
    -0.10
    lug
    -0.10
    POSITIVE LOGITS
    nel
    0.09
     greetings
    0.08
     Rut
    0.08
     Pessoa
    0.07
    uther
    0.07
     tritur
    0.07
    .biz
    0.07
    assin
    0.07
    Greetings
    0.07
    vo
    0.07
    Activations Density 0.000%

    No Known Activations