© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 115592
    Prev
    Next
    INDEX
    Explanations

    insult, encouragement, calling, threats, praise

    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
     Recomm
    -0.10
     Hanson
    -0.10
     Rating
    -0.10
     Tun
    -0.10
    inas
    -0.09
     tun
    -0.09
     pil
    -0.09
     demonstration
    -0.09
     greeting
    -0.09
     courtesy
    -0.09
    POSITIVE LOGITS
    /prom
    0.10
     about
    0.10
     Blasio
    0.10
    Sink
    0.09
     Sink
    0.09
    /comment
    0.09
    utely
    0.09
     pivot
    0.09
    464
    0.09
     lav
    0.09
    Activations Density 0.039%

    No Known Activations