© 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. 6775
    Prev
    Next
    INDEX
    Explanations

    whatsapp features

    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
     sometimes
    -0.10
    Âł
    -0.09
     sprinkle
    -0.09
     Amer
    -0.09
     Hust
    -0.09
    sometimes
    -0.09
     billed
    -0.09
     sprink
    -0.09
    
    -0.09
     Lam
    -0.08
    POSITIVE LOGITS
    gne
    0.10
    gnore
    0.10
    Impossible
    0.09
     eyes
    0.09
     Deus
    0.09
    dle
    0.09
     hearing
    0.09
    ango
    0.09
     heard
    0.08
    Č
    0.08
    Activations Density 0.008%

    No Known Activations