© 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. 89473
    Prev
    Next
    INDEX
    Explanations

    forms of "appear"

    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
     Shaw
    -0.11
    oti
    -0.10
    lin
    -0.10
    ori
    -0.10
    ti
    -0.10
    arias
    -0.10
     heck
    -0.10
    tor
    -0.10
    display
    -0.09
    ashi
    -0.09
    POSITIVE LOGITS
    /dis
    0.18
    antly
    0.17
    ances
    0.14
    angel
    0.12
    ants
    0.11
    antal
    0.11
    nces
    0.11
     destined
    0.10
    asing
    0.09
    stance
    0.09
    Activations Density 0.137%

    No Known Activations