© 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. 15006
    Prev
    Next
    INDEX
    Explanations

    technical terms

    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
     –↵↵
    -0.11
    âĢ¦and
    -0.11
     righteous
    -0.10
    ikon
    -0.10
     Covenant
    -0.09
     –
    -0.09
     âĢķ
    -0.09
     (?)
    -0.09
     ostensibly
    -0.09
    uh
    -0.09
    POSITIVE LOGITS
     fus
    0.10
     stret
    0.08
    chrono
    0.08
    IndexOf
    0.08
    ivant
    0.08
    coc
    0.08
    acic
    0.08
     nurture
    0.08
     blij
    0.07
     immobil
    0.07
    Activations Density 0.014%

    No Known Activations