© 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. 116671
    Prev
    Next
    INDEX
    Explanations

    bot or chatbot related vocabulary

    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
     DVR
    -0.10
     electronically
    -0.10
     biome
    -0.10
    dsp
    -0.10
     Inhal
    -0.09
    DAC
    -0.09
    nex
    -0.09
     Monaco
    -0.09
     photographers
    -0.09
     uploader
    -0.09
    POSITIVE LOGITS
     bot
    0.25
     convers
    0.23
     chat
    0.23
     Bot
    0.22
     bots
    0.21
    -bot
    0.21
    bot
    0.20
     Convers
    0.20
    Bot
    0.20
    -chat
    0.19
    Activations Density 0.501%

    No Known Activations