© 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. 28459
    Prev
    Next
    INDEX
    Explanations

    gifts and related concepts

    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
    _mk
    -0.09
     Hawk
    -0.08
     Sunset
    -0.08
     pct
    -0.08
    yte
    -0.08
     Leer
    -0.08
    entic
    -0.08
     tread
    -0.08
     Fax
    -0.08
    els
    -0.08
    POSITIVE LOGITS
    gift
    0.12
     wrapping
    0.12
    wrapped
    0.12
    ufe
    0.11
     gift
    0.11
     Gift
    0.11
    /inc
    0.11
    amu
    0.11
     gifted
    0.11
    egl
    0.11
    Activations Density 0.006%

    No Known Activations