© 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. 50209
    Prev
    Next
    INDEX
    Explanations

    will not

    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
    lg
    -0.10
    anim
    -0.09
    .sb
    -0.09
     disregard
    -0.09
     IW
    -0.08
    .sf
    -0.08
    iren
    -0.08
    ighth
    -0.08
    htable
    -0.08
    avenport
    -0.08
    POSITIVE LOGITS
     gonna
    0.23
     won
    0.19
     will
    0.17
     wont
    0.17
     WILL
    0.16
    Won
    0.16
    ä¼ļ
    0.16
     magically
    0.15
    will
    0.15
     Won
    0.15
    Activations Density 0.113%

    No Known Activations