© 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. 32177
    Prev
    Next
    INDEX
    Explanations

    quality of

    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
     proper
    -0.08
     percentages
    -0.08
     relative
    -0.08
    976
    -0.08
     amounts
    -0.07
     tendencies
    -0.07
     impr
    -0.07
    quelle
    -0.07
     familiar
    -0.07
     Santos
    -0.07
    POSITIVE LOGITS
     craftsmanship
    0.18
     quality
    0.16
    quality
    0.15
    -quality
    0.14
     Quality
    0.14
    Quality
    0.13
    manship
    0.13
     interactions
    0.12
     ENC
    0.12
     output
    0.12
    Activations Density 0.218%

    No Known Activations