© 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. 50215
    Prev
    Next
    INDEX
    Explanations

    scale related terms

    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
     unp
    -0.09
     gener
    -0.09
    Expose
    -0.08
    icle
    -0.08
     slightest
    -0.08
     Clown
    -0.08
     literal
    -0.07
    Untitled
    -0.07
     unrecognized
    -0.07
    inden
    -0.07
    POSITIVE LOGITS
    ced
    0.11
    /embed
    0.10
    IEL
    0.10
    itus
    0.10
    /post
    0.10
     Rif
    0.10
     Gad
    0.10
     conception
    0.10
    ables
    0.09
    lauf
    0.09
    Activations Density 0.005%

    No Known Activations