© 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. 32496
    Prev
    Next
    INDEX
    Explanations

    phrase for it

    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
    vic
    -0.11
    oland
    -0.09
    vac
    -0.09
    ewe
    -0.08
    summ
    -0.08
    _corner
    -0.08
    plat
    -0.08
     Sever
    -0.08
     dbs
    -0.08
     conspic
    -0.08
    POSITIVE LOGITS
     word
    0.54
     Word
    0.41
    word
    0.40
     WORD
    0.38
    Word
    0.38
    -word
    0.37
    _word
    0.33
     words
    0.32
    WORD
    0.31
    (word
    0.31
    Activations Density 0.052%

    No Known Activations