© 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. 28564
    Prev
    Next
    INDEX
    Explanations

    session / sessions

    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
     pond
    -0.10
     parade
    -0.09
    isp
    -0.08
     novelty
    -0.08
    zie
    -0.08
    967
    -0.08
     gossip
    -0.08
     jur
    -0.08
    irts
    -0.08
     Exhibit
    -0.08
    POSITIVE LOGITS
     session
    0.57
     sessions
    0.55
     Sessions
    0.44
     Session
    0.44
    -session
    0.43
    session
    0.40
    Session
    0.39
     sess
    0.38
     SESSION
    0.38
    /session
    0.37
    Activations Density 0.110%

    No Known Activations