© 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. 116803
    Prev
    Next
    INDEX
    Explanations

    conversation and adaptation

    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
     purity
    -0.10
     sex
    -0.10
     nomin
    -0.10
     Mama
    -0.09
    criptor
    -0.09
    obao
    -0.09
    oven
    -0.09
    872
    -0.09
     Lov
    -0.09
     Hat
    -0.09
    POSITIVE LOGITS
     conversation
    0.17
     convers
    0.16
     converse
    0.15
     Convers
    0.15
     effortlessly
    0.15
     Conversation
    0.14
     etiquette
    0.14
     adapt
    0.14
     conversations
    0.14
     accompany
    0.13
    Activations Density 0.014%

    No Known Activations