© 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. 7183
    Prev
    Next
    INDEX
    Explanations

    copy of this

    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
    ibs
    -0.10
     Bonds
    -0.09
    paces
    -0.08
     Ferry
    -0.08
     Sor
    -0.08
     Ents
    -0.08
    NCY
    -0.08
    /Users
    -0.08
     squat
    -0.08
    ahas
    -0.08
    POSITIVE LOGITS
    chen
    0.10
    arkan
    0.09
    chin
    0.09
     AMA
    0.09
     Charl
    0.09
    asc
    0.08
     metam
    0.08
     trembling
    0.08
    /query
    0.08
     mine
    0.08
    Activations Density 0.003%

    No Known Activations