© 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. 17720
    Prev
    Next
    INDEX
    Explanations

    causing harm or changes

    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
     nuisance
    -0.10
     Fe
    -0.09
     ideally
    -0.09
    rios
    -0.09
     Comfort
    -0.09
     Zur
    -0.08
     Balt
    -0.08
     Het
    -0.08
     unintention
    -0.08
     Conway
    -0.08
    POSITIVE LOGITS
     magically
    0.14
    Will
    0.12
     WILL
    0.12
     infertility
    0.12
     spontaneously
    0.12
    rots
    0.12
     cancer
    0.11
     cure
    0.11
     Will
    0.11
     shrink
    0.11
    Activations Density 0.055%

    No Known Activations