© 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. 113049
    Prev
    Next
    INDEX
    Explanations

    invites, guests, or social gatherings

    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
     Demp
    -0.10
    ceptor
    -0.09
     baj
    -0.09
    yk
    -0.09
     diam
    -0.08
     Dom
    -0.08
     nich
    -0.08
     Bod
    -0.08
     specialized
    -0.08
     rehearsal
    -0.08
    POSITIVE LOGITS
     invites
    0.14
     encounters
    0.14
     guest
    0.13
     swinging
    0.13
     yourselves
    0.13
    swing
    0.13
     swing
    0.12
     invite
    0.12
     swings
    0.12
     collectively
    0.12
    Activations Density 0.023%

    No Known Activations