© 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
    2. Olmo-3-1125-32B
    3. 32-RES-BATCHTOPK-131K
    4. 14612
    Prev
    Next
    INDEX
    Explanations

    wearing clothes or accessories

    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
    aus
    -0.10
    .IT
    -0.10
     jig
    -0.10
    rvine
    -0.10
    Houston
    -0.10
     Islands
    -0.10
    Scaled
    -0.10
    tok
    -0.09
     tls
    -0.09
     Alps
    -0.09
    POSITIVE LOGITS
     no
    0.11
     goggles
    0.11
     headphones
    0.10
     minimal
    0.09
     glasses
    0.09
     gloves
    0.09
     strict
    0.09
     fewer
    0.09
     virtual
    0.08
    bish
    0.08
    Activations Density 0.005%

    No Known Activations