© 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. 27375
    Prev
    Next
    INDEX
    Explanations

    string 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
     parity
    -0.11
    eki
    -0.10
    eda
    -0.10
     Lamb
    -0.10
     lamb
    -0.09
     diffuse
    -0.09
    parity
    -0.09
     Harvey
    -0.09
     spanking
    -0.09
     reversible
    -0.09
    POSITIVE LOGITS
     attached
    0.15
     Attached
    0.14
    attached
    0.14
     strings
    0.13
    strings
    0.12
    Attached
    0.11
    æĿŁ
    0.10
     wield
    0.10
    (strings
    0.09
    enberg
    0.09
    Activations Density 0.001%

    No Known Activations