© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 113511
    Prev
    Next
    INDEX
    Explanations

    mate, matej, mateo, quality, choice

    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
     Proud
    -0.10
    aug
    -0.09
    gend
    -0.09
     Sabb
    -0.09
     Je
    -0.09
    gings
    -0.08
    alem
    -0.08
    cq
    -0.08
    gnore
    -0.08
    lane
    -0.08
    POSITIVE LOGITS
     Maher
    0.10
    usz
    0.10
     Mate
    0.09
     runaway
    0.09
    otime
    0.09
     Mag
    0.09
     Brady
    0.09
     Assigned
    0.09
     meas
    0.09
    yo
    0.09
    Activations Density 0.009%

    No Known Activations