© 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. 29835
    Prev
    Next
    INDEX
    Explanations

    clown, cat, puss

    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
    Loop
    -0.12
     brushed
    -0.11
    egen
    -0.11
     Platt
    -0.11
     enact
    -0.11
    oyer
    -0.10
     forged
    -0.10
    yleft
    -0.10
     Trem
    -0.10
    ead
    -0.10
    POSITIVE LOGITS
     clown
    0.09
     puss
    0.07
     pus
    0.07
     Clown
    0.07
    åįİ
    0.07
     twin
    0.07
     synopsis
    0.07
     Zum
    0.07
    jian
    0.06
     cat
    0.06
    Activations Density 0.001%

    No Known Activations