© 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. 5569
    Prev
    Next
    INDEX
    Explanations

    how did you get/achieve/do

    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
     Seas
    -0.09
     sacrificing
    -0.08
    icks
    -0.08
    åij
    -0.08
    ót
    -0.08
     Attention
    -0.08
     Av
    -0.08
     cur
    -0.08
    ноÑģÑĤи
    -0.08
    ees
    -0.07
    POSITIVE LOGITS
     guessed
    0.14
     guess
    0.13
     knew
    0.11
     know
    0.11
    adem
    0.11
     blunt
    0.10
    locate
    0.10
     guesses
    0.10
    usc
    0.10
     Unt
    0.10
    Activations Density 0.005%

    No Known Activations