© 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. 46635
    Prev
    Next
    INDEX
    Explanations

    handball

    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
     hands
    -0.11
    ting
    -0.11
    ardy
    -0.10
    ë¶Ħ
    -0.10
    chet
    -0.10
     Hands
    -0.09
    uem
    -0.09
    odon
    -0.09
    Ìģ
    -0.09
    head
    -0.09
    POSITIVE LOGITS
    icap
    0.22
    crafted
    0.20
    ker
    0.20
    /arm
    0.19
    picked
    0.18
    rails
    0.17
    rail
    0.17
    maid
    0.15
    -held
    0.15
    shake
    0.15
    Activations Density 0.097%

    No Known Activations