© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 114930
    Prev
    Next
    INDEX
    Explanations

    offer/ere suffix

    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
     msm
    -0.10
    assel
    -0.09
    toa
    -0.09
    nex
    -0.09
     defer
    -0.09
    _pb
    -0.09
    antar
    -0.09
     Chick
    -0.09
     Buff
    -0.09
     Pru
    -0.09
    POSITIVE LOGITS
     ere
    0.09
    ERE
    0.08
     ing
    0.08
     rak
    0.08
    .cf
    0.08
    ners
    0.08
    #!/
    0.08
     rit
    0.08
    ere
    0.07
     Ce
    0.07
    Activations Density 0.117%

    No Known Activations