© 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. 28731
    Prev
    Next
    INDEX
    Explanations

    defining the goal 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
    ees
    -0.13
    ally
    -0.13
    eer
    -0.12
    esco
    -0.12
    ation
    -0.11
    elor
    -0.10
    asset
    -0.10
    ations
    -0.10
    s
    -0.10
    esting
    -0.10
    POSITIVE LOGITS
    posts
    0.17
    set
    0.14
    keepers
    0.13
    -setting
    0.12
    -oriented
    0.12
    setting
    0.11
     posts
    0.10
    post
    0.10
     Posts
    0.09
    setter
    0.09
    Activations Density 0.034%

    No Known Activations