© 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. 92046
    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
    &r
    -0.10
     ROM
    -0.08
    Bell
    -0.08
    ns
    -0.08
     presentations
    -0.08
    &R
    -0.08
     Bell
    -0.08
    á»įn
    -0.08
    ROM
    -0.07
     Kimber
    -0.07
    POSITIVE LOGITS
    jaw
    0.10
     Jab
    0.10
     Orig
    0.10
     Pang
    0.10
     Morton
    0.10
    ook
    0.10
     discretionary
    0.10
     terra
    0.09
    elda
    0.09
    alone
    0.09
    Activations Density 0.000%

    No Known Activations