© 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. 29885
    Prev
    Next
    INDEX
    Explanations

    category:

    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
    yster
    -0.08
     vit
    -0.08
    adera
    -0.08
     Hast
    -0.08
     fires
    -0.08
     reserved
    -0.08
     hob
    -0.08
     verbally
    -0.07
     believing
    -0.07
    urally
    -0.07
    POSITIVE LOGITS
     converse
    0.11
     country
    0.11
    coop
    0.10
    cca
    0.10
     intimid
    0.10
    gran
    0.10
    PROP
    0.10
     ornament
    0.10
     medio
    0.09
    country
    0.09
    Activations Density 0.006%

    No Known Activations