© 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. 48165
    Prev
    Next
    INDEX
    Explanations

    words starting with Sz

    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
     bud
    -0.10
     Bud
    -0.10
    ovan
    -0.09
    æŀľ
    -0.08
    bourne
    -0.08
     Heavy
    -0.08
    delegate
    -0.08
     Budd
    -0.08
     lon
    -0.08
     budding
    -0.08
    POSITIVE LOGITS
    iry
    0.11
    pun
    0.11
    abo
    0.10
    pty
    0.10
    crest
    0.09
    Ñĥм
    0.09
     blasts
    0.09
     fals
    0.09
    ews
    0.09
    mlin
    0.09
    Activations Density 0.005%

    No Known Activations