© 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. 14685
    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
     gv
    -0.13
     nomin
    -0.13
    edm
    -0.12
    ferred
    -0.12
    ropy
    -0.12
    erre
    -0.12
    omat
    -0.12
     glue
    -0.12
    edback
    -0.12
    ingo
    -0.12
    POSITIVE LOGITS
     flirt
    0.08
     Sultan
    0.07
     attitude
    0.07
     attitudes
    0.07
     charm
    0.06
    eec
    0.06
     theatrical
    0.06
     playful
    0.06
    croft
    0.06
     handling
    0.06
    Activations Density 0.000%

    No Known Activations