© 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. 116830
    Prev
    Next
    INDEX
    Explanations

    descriptive, confident, transformative, innovative, epic, simple, wet, hot, rural

    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
    anga
    -0.10
     foremost
    -0.09
    +a
    -0.09
     hassle
    -0.09
    est
    -0.09
    éł
    -0.09
    IPA
    -0.09
     Mans
    -0.09
     %=
    -0.09
     ing
    -0.09
    POSITIVE LOGITS
    -than
    0.10
    -fe
    0.10
    /use
    0.10
    (and
    0.10
    —and
    0.09
    —but
    0.08
    —even
    0.08
    /power
    0.08
     Encore
    0.08
     (!
    0.08
    Activations Density 0.180%

    No Known Activations