© 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. 88227
    Prev
    Next
    INDEX
    Explanations

    join us or connect with me

    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
    rio
    -0.13
    abin
    -0.13
    losure
    -0.11
    vault
    -0.11
     him
    -0.11
     Hond
    -0.10
     Rooney
    -0.10
     relative
    -0.10
     happily
    -0.10
     Bair
    -0.10
    POSITIVE LOGITS
     sometime
    0.16
     anytime
    0.14
     soon
    0.12
     today
    0.11
     tonight
    0.11
     someday
    0.09
    aggi
    0.09
    today
    0.09
     come
    0.08
    contr
    0.08
    Activations Density 0.023%

    No Known Activations