© 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. 17495
    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
    asca
    -0.11
     ê³Ħ
    -0.10
    ide
    -0.10
     [|
    -0.10
    ustral
    -0.09
     departure
    -0.09
    hci
    -0.09
    csi
    -0.09
     Gratuit
    -0.09
    uchi
    -0.09
    POSITIVE LOGITS
     behold
    0.09
     Stern
    0.09
     Ton
    0.09
    feat
    0.09
    SV
    0.09
     Howell
    0.08
    -lo
    0.08
     coached
    0.08
     cultivated
    0.08
     addicted
    0.08
    Activations Density 0.000%

    No Known Activations