© 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. 7133
    Prev
    Next
    INDEX
    Explanations

    gift or gifts

    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
    ynos
    -0.10
     cooperate
    -0.10
     absorbing
    -0.09
     chatting
    -0.09
     sliders
    -0.09
     Dich
    -0.09
     drills
    -0.09
     Vere
    -0.09
    preserve
    -0.09
     cooper
    -0.09
    POSITIVE LOGITS
     gifts
    0.39
     gift
    0.38
     Gifts
    0.36
    Gift
    0.33
     Gift
    0.33
    gift
    0.29
    _gift
    0.27
    éĢģ
    0.22
     gifted
    0.22
     gesture
    0.21
    Activations Density 0.057%

    No Known Activations