© 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. 49717
    Prev
    Next
    INDEX
    Explanations

    javascript getAttribute

    np_acts-logits-general · gemini-2.5-flash-lite
    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
    rez
    -0.09
    fv
    -0.09
     Simpsons
    -0.09
    744
    -0.09
    elin
    -0.09
    CCA
    -0.09
    ilian
    -0.09
    icl
    -0.09
     condemn
    -0.09
    rels
    -0.09
    POSITIVE LOGITS
     Kund
    0.10
     Painter
    0.08
     Pis
    0.08
    JE
    0.08
     regularly
    0.08
     erectile
    0.08
    /change
    0.08
     boils
    0.07
    _Common
    0.07
     indul
    0.07
    Activations Density 0.039%

    No Known Activations