© 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. 114490
    Prev
    Next
    INDEX
    Explanations

    shut and be thought

    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
     Laz
    -0.10
    GRID
    -0.09
    Splash
    -0.09
     Sponsor
    -0.09
     fuse
    -0.09
     hes
    -0.09
    dio
    -0.09
     contingency
    -0.09
    ocused
    -0.09
     Herald
    -0.09
    POSITIVE LOGITS
     doubly
    0.12
    reta
    0.11
    icut
    0.10
    inta
    0.10
    -es
    0.09
     Ko
    0.09
    /th
    0.09
     impossible
    0.09
     Impossible
    0.09
     Doyle
    0.09
    Activations Density 0.448%

    No Known Activations