© 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. 48256
    Prev
    Next
    INDEX
    Explanations

    making stronger or more certain

    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
    oppable
    -0.11
    form
    -0.11
    rove
    -0.11
    inati
    -0.10
     freely
    -0.10
    juan
    -0.10
    rick
    -0.10
     Maison
    -0.10
    endants
    -0.10
    imin
    -0.10
    POSITIVE LOGITS
     positive
    0.09
     ster
    0.09
     stereotypes
    0.08
     boundaries
    0.08
     lax
    0.08
    positive
    0.07
     positivity
    0.07
     steel
    0.07
     existing
    0.07
     suspicion
    0.07
    Activations Density 0.031%

    No Known Activations