© 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. 50090
    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
    orial
    -0.11
    vak
    -0.10
     hobbies
    -0.09
    CEL
    -0.09
     hobby
    -0.09
     Stern
    -0.09
     creep
    -0.09
    Äįe
    -0.09
    atal
    -0.09
    aland
    -0.09
    POSITIVE LOGITS
     canon
    0.09
     Scotch
    0.09
     Nich
    0.08
    optic
    0.08
    fmt
    0.08
    Animator
    0.08
     Specs
    0.08
     requisite
    0.08
     bon
    0.08
     lieutenant
    0.08
    Activations Density 0.000%

    No Known Activations