© 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. 4212
    Prev
    Next
    INDEX
    Explanations

    asking for help or explanation

    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
     pretext
    -0.08
    ocks
    -0.08
    lian
    -0.08
    -validator
    -0.07
    obic
    -0.07
    POOL
    -0.07
     Everyday
    -0.07
    cq
    -0.07
     disclosed
    -0.07
     Inch
    -0.07
    POSITIVE LOGITS
     anyone
    0.64
     Anyone
    0.61
     anybody
    0.61
    Anyone
    0.56
     somebody
    0.27
     someone
    0.27
    any
    0.25
    -any
    0.23
     Has
    0.23
    Has
    0.23
    Activations Density 1.589%

    No Known Activations