© 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. 114411
    Prev
    Next
    INDEX
    Explanations

    companionship and assistance

    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
     consenting
    -0.11
     taboo
    -0.10
    onica
    -0.10
     voluntarily
    -0.10
     perverse
    -0.10
     Bedroom
    -0.10
     habitual
    -0.09
    san
    -0.09
     weekly
    -0.09
    $i
    -0.09
    POSITIVE LOGITS
     companions
    0.21
     accompany
    0.20
     companion
    0.17
     accompanying
    0.17
     accompanies
    0.17
     distracting
    0.16
     assistance
    0.14
     accompanied
    0.14
     impress
    0.13
     complement
    0.13
    Activations Density 0.039%

    No Known Activations