© 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. 117045
    Prev
    Next
    INDEX
    Explanations

    contribute, helpful, usefulness

    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
     bour
    -0.08
     cheating
    -0.08
    ãĤ°
    -0.08
    pedia
    -0.08
     Cruz
    -0.08
     merciless
    -0.08
     forcibly
    -0.07
     dal
    -0.07
     Ack
    -0.07
    (AF
    -0.07
    POSITIVE LOGITS
     usefulness
    0.49
     useful
    0.45
     contribution
    0.41
     Useful
    0.39
     contribute
    0.38
     Contribution
    0.37
     contributing
    0.35
     contributes
    0.34
     contributions
    0.34
     helpful
    0.34
    Activations Density 0.839%

    No Known Activations