© 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
    2. Olmo-3-1125-32B
    3. 32-RES-BATCHTOPK-131K
    4. 91868
    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
     nom
    -0.09
    conj
    -0.08
    agar
    -0.08
     numer
    -0.07
    gar
    -0.07
     successive
    -0.07
    oker
    -0.07
    ç«
    -0.07
     Brock
    -0.07
     conj
    -0.06
    POSITIVE LOGITS
    mers
    0.12
     Riv
    0.11
    avors
    0.11
    Ctr
    0.11
    stants
    0.11
    ildo
    0.10
    inho
    0.10
    IMER
    0.10
    emark
    0.10
    oba
    0.10
    Activations Density 0.000%

    No Known Activations