© 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. 17149
    Prev
    Next
    INDEX
    Explanations

    changes, immune, policies, studies

    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
     internally
    -0.09
     disproportionate
    -0.09
     improbable
    -0.08
     uniquely
    -0.08
     ingenious
    -0.08
     seh
    -0.07
     herald
    -0.07
     disproportionately
    -0.07
     unten
    -0.07
     arousal
    -0.07
    POSITIVE LOGITS
    ness
    0.13
    NESS
    0.12
     collection
    0.12
     endeavor
    0.11
    /Common
    0.11
    -cur
    0.11
    (er
    0.11
    rna
    0.11
     Heal
    0.11
     creations
    0.11
    Activations Density 0.003%

    No Known Activations