© 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. 27950
    Prev
    Next
    INDEX
    Explanations

    perfect or ideal for

    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
    nth
    -0.10
     Quarter
    -0.09
    adam
    -0.09
    avail
    -0.09
     mere
    -0.08
    Quarter
    -0.08
    osi
    -0.08
     contagious
    -0.08
     Brief
    -0.08
    _scr
    -0.08
    POSITIVE LOGITS
     suited
    0.10
     anytime
    0.09
     balance
    0.09
    -fit
    0.09
     prim
    0.09
     Rath
    0.09
     accompanying
    0.09
     complement
    0.09
     zw
    0.09
     Wright
    0.09
    Activations Density 0.018%

    No Known Activations