© 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. 112495
    Prev
    Next
    INDEX
    Explanations

    originating from

    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
     Kathy
    -0.08
    usch
    -0.08
    itr
    -0.07
     whit
    -0.07
    alive
    -0.07
     subordinate
    -0.07
    ASCII
    -0.07
     Hilton
    -0.07
    Fred
    -0.06
     ground
    -0.06
    POSITIVE LOGITS
     native
    0.35
     originating
    0.33
     origins
    0.30
     hometown
    0.30
     originate
    0.30
     origin
    0.29
     nationality
    0.28
     originates
    0.28
    native
    0.28
     hail
    0.28
    Activations Density 0.919%

    No Known Activations