© 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. 91143
    Prev
    Next
    INDEX
    Explanations

    object/URL/meta/frequency/null/podcast/father/ge/scene followed by suffixes

    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
    722
    -0.10
    traction
    -0.09
     kre
    -0.08
    tractive
    -0.08
    ings
    -0.08
    bras
    -0.08
    clusion
    -0.08
    rait
    -0.08
    oth
    -0.08
    attr
    -0.08
    POSITIVE LOGITS
    lessly
    0.17
    orarily
    0.14
    elize
    0.14
    antically
    0.13
    ographically
    0.12
    ishly
    0.12
    ologically
    0.12
     brainstorm
    0.12
    etically
    0.11
    ify
    0.11
    Activations Density 0.223%

    No Known Activations