© 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. 50172
    Prev
    Next
    INDEX
    Explanations

    suppose and supposed

    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
    MUX
    -0.11
    PLUS
    -0.09
    iar
    -0.08
     swingers
    -0.08
    wap
    -0.08
    rez
    -0.08
     swinger
    -0.08
    rete
    -0.08
    spot
    -0.08
     decis
    -0.08
    POSITIVE LOGITS
    umably
    0.11
    ess
    0.10
    ide
    0.10
     contrario
    0.10
    umed
    0.10
    ibile
    0.09
    ised
    0.09
    unwrap
    0.09
     mdl
    0.09
    eb
    0.09
    Activations Density 0.009%

    No Known Activations