© 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. 88035
    Prev
    Next
    INDEX
    Explanations

    notifications, email addresses, and errors

    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
     Bernstein
    -0.09
    elin
    -0.09
    usher
    -0.08
     Briggs
    -0.08
    (Py
    -0.08
     Elk
    -0.08
     ribs
    -0.08
     Vad
    -0.08
     intervene
    -0.08
    amil
    -0.08
    POSITIVE LOGITS
     Sebast
    0.10
     stranger
    0.10
    nl
    0.10
    ono
    0.10
     strangers
    0.10
    ONO
    0.10
     Stranger
    0.10
    .ur
    0.09
    Foreign
    0.09
     Scalars
    0.09
    Activations Density 0.001%

    No Known Activations