© 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. 31034
    Prev
    Next
    INDEX
    Explanations

    INFO

    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
     SEA
    -0.08
     flirting
    -0.08
     inf
    -0.08
     Fortress
    -0.08
     kin
    -0.08
    ย
    -0.08
     fond
    -0.08
     sketch
    -0.07
     Marcel
    -0.07
    apt
    -0.07
    POSITIVE LOGITS
    lein
    0.10
     honoured
    0.10
     tur
    0.10
     congrat
    0.09
    Bubble
    0.09
     Catch
    0.09
     Busy
    0.09
     operand
    0.09
    illas
    0.09
     ethic
    0.09
    Activations Density 0.320%

    No Known Activations