© 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. 47205
    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
     chalk
    -0.10
    owa
    -0.10
    ched
    -0.09
    ë¦Ħ
    -0.09
     Rot
    -0.09
     calculus
    -0.09
    dyn
    -0.09
    685
    -0.08
     mechan
    -0.08
    resh
    -0.08
    POSITIVE LOGITS
    fits
    0.09
    DSP
    0.09
     qual
    0.09
     Sunny
    0.09
     hod
    0.09
    ioneer
    0.09
     undergone
    0.09
    .pb
    0.09
     ull
    0.09
    kok
    0.09
    Activations Density 0.000%

    No Known Activations