© 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. 17982
    Prev
    Next
    INDEX
    Explanations

    purchase tickets

    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
     nearest
    -0.10
     kitty
    -0.10
    oric
    -0.10
    atoria
    -0.09
     readiness
    -0.09
    olg
    -0.09
     clustering
    -0.09
    ochen
    -0.09
    obel
    -0.09
    082
    -0.08
    POSITIVE LOGITS
     tickets
    0.44
     Tickets
    0.38
     ticket
    0.32
    Tickets
    0.29
    tickets
    0.29
     Ticket
    0.29
    _tickets
    0.24
    -ticket
    0.24
    Ticket
    0.24
     TICK
    0.22
    Activations Density 0.108%

    No Known Activations