© 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. 25881
    Prev
    Next
    INDEX
    Explanations

    comparative positive descriptors

    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
     enough
    -0.11
    arna
    -0.10
    arn
    -0.10
    iran
    -0.10
    gom
    -0.10
    kim
    -0.10
     mixing
    -0.09
     suff
    -0.09
    lee
    -0.09
    asis
    -0.09
    POSITIVE LOGITS
     penis
    0.11
     diplom
    0.09
     paycheck
    0.09
    ogh
    0.08
    imap
    0.08
     initials
    0.08
     stature
    0.08
    enge
    0.08
     Penis
    0.08
     happier
    0.07
    Activations Density 0.011%

    No Known Activations