© 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. 90393
    Prev
    Next
    INDEX
    Explanations

    support for

    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
    eti
    -0.10
    horn
    -0.10
     pract
    -0.10
    boro
    -0.10
     USERS
    -0.10
     Tu
    -0.09
     Bor
    -0.09
    Reports
    -0.09
    ков
    -0.09
    isia
    -0.09
    POSITIVE LOGITS
    ive
    0.22
    /support
    0.17
    iveness
    0.17
    ively
    0.14
    IVE
    0.14
    .Support
    0.13
     Support
    0.13
     support
    0.13
    ingly
    0.12
    Support
    0.12
    Activations Density 0.096%

    No Known Activations