© 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. 5908
    Prev
    Next
    INDEX
    Explanations

    seeking information or assistance

    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
     affiliation
    -0.10
    eton
    -0.10
    isel
    -0.10
    PX
    -0.10
     Gew
    -0.09
     inhabit
    -0.09
    FW
    -0.09
    -P
    -0.09
    -comp
    -0.09
    endez
    -0.09
    POSITIVE LOGITS
     Salv
    0.09
     Alger
    0.09
     Camb
    0.09
     ABOUT
    0.09
    kok
    0.09
    alsa
    0.08
     inquire
    0.08
     Barber
    0.08
     Mystery
    0.08
     nei
    0.08
    Activations Density 0.116%

    No Known Activations