© 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. 25537
    Prev
    Next
    INDEX
    Explanations

    drug discussions by, Putin has, petrol last, junction are, head permitted, birth is, activation are, inmates who, declines is, -over during

    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
    iaux
    -0.08
    kee
    -0.07
     Wander
    -0.07
    Unload
    -0.07
     SM
    -0.07
     WOW
    -0.07
    atr
    -0.07
    :].
    -0.07
     Mill
    -0.07
    ãĢĤ(
    -0.07
    POSITIVE LOGITS
     certainly
    0.13
     fortunately
    0.13
     unfortunately
    0.13
     complic
    0.12
     undoubtedly
    0.12
     proved
    0.12
     greatly
    0.12
    ,is
    0.11
    ema
    0.11
     nevertheless
    0.11
    Activations Density 0.915%

    No Known Activations