© 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. 18269
    Prev
    Next
    INDEX
    Explanations

    criticism or critiques

    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
     cane
    -0.09
     frag
    -0.09
    ded
    -0.09
    ing
    -0.09
    unya
    -0.09
     Wig
    -0.09
    /ge
    -0.09
    egin
    -0.09
     heraus
    -0.09
    cent
    -0.08
    POSITIVE LOGITS
    /question
    0.12
    /comment
    0.11
    /questions
    0.11
    ser
    0.10
    /mock
    0.10
    icism
    0.09
     harsh
    0.09
    izers
    0.09
    uer
    0.09
    /op
    0.09
    Activations Density 0.011%

    No Known Activations