© 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. 48804
    Prev
    Next
    INDEX
    Explanations

    thanks for clarification or insights

    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
    TPL
    -0.11
     thanked
    -0.11
    chosen
    -0.11
    CBS
    -0.11
    Reuse
    -0.10
    antz
    -0.10
     Pols
    -0.10
     Thank
    -0.10
    iza
    -0.10
     Treat
    -0.10
    POSITIVE LOGITS
     informative
    0.14
     clar
    0.13
     insight
    0.13
     enlight
    0.13
     clarified
    0.12
     insights
    0.11
     clarification
    0.11
     information
    0.11
     enlightenment
    0.10
     informing
    0.10
    Activations Density 0.023%

    No Known Activations