© 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. 33341
    Prev
    Next
    INDEX
    Explanations

    new activities become

    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
    utsch
    -0.10
     Garr
    -0.09
    arger
    -0.09
    OTO
    -0.08
    bau
    -0.08
    !!,
    -0.08
     despite
    -0.08
    poss
    -0.08
     :(
    -0.08
     resisted
    -0.08
    POSITIVE LOGITS
     becomes
    0.16
     transformed
    0.15
     never
    0.14
     suddenly
    0.13
     synonymous
    0.12
     enriched
    0.12
     become
    0.12
     redefine
    0.12
     indeed
    0.12
     nowhere
    0.12
    Activations Density 0.091%

    No Known Activations