© 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. 5367
    Prev
    Next
    INDEX
    Explanations

    that is,

    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
    orum
    -0.12
     deser
    -0.12
    OMP
    -0.11
    oled
    -0.11
    |int
    -0.11
     Kay
    -0.10
     vault
    -0.10
     lint
    -0.10
    anni
    -0.10
    dek
    -0.10
    POSITIVE LOGITS
     unless
    0.11
    ,
    0.10
    -to
    0.09
     why
    0.09
    ogs
    0.08
     ave
    0.08
    jam
    0.08
     if
    0.07
     Kash
    0.07
    :
    0.07
    Activations Density 0.045%

    No Known Activations