© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 50645
    Prev
    Next
    INDEX
    Explanations

    mix of words and / or tape

    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
    ellido
    -0.10
    zoek
    -0.09
    ed
    -0.09
    ATS
    -0.08
     allot
    -0.08
    sworth
    -0.08
    utches
    -0.08
    staking
    -0.08
    OUCH
    -0.08
    ftar
    -0.08
    POSITIVE LOGITS
    tures
    0.17
     mix
    0.13
    /max
    0.13
    (es
    0.13
     Mix
    0.12
    tape
    0.12
    ael
    0.11
     Bust
    0.11
    ery
    0.11
    dj
    0.11
    Activations Density 0.007%

    No Known Activations