© 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. 90799
    Prev
    Next
    INDEX
    Explanations

    suffix "-es" or "-os" or "-oz"

    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
    ouro
    -0.12
     definite
    -0.10
    enes
    -0.10
    OTH
    -0.10
    wind
    -0.10
    ACES
    -0.09
     DES
    -0.09
     Dear
    -0.09
    ungs
    -0.09
     vois
    -0.09
    POSITIVE LOGITS
     dripping
    0.15
     oo
    0.12
     crawl
    0.12
     drip
    0.12
     crawling
    0.12
    zie
    0.11
     dri
    0.10
    /sl
    0.10
    lette
    0.10
     bleeding
    0.10
    Activations Density 0.001%

    No Known Activations