© 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. 33342
    Prev
    Next
    INDEX
    Explanations

    names of people or groups

    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
     subsequently
    -0.10
     afterward
    -0.10
     forgiving
    -0.10
     disappe
    -0.09
     thereby
    -0.09
     eventual
    -0.09
     thereafter
    -0.09
    iese
    -0.09
    bies
    -0.09
    ¾
    -0.09
    POSITIVE LOGITS
     wants
    0.14
     knows
    0.13
     loves
    0.13
     woke
    0.13
     couldn
    0.12
     want
    0.12
     sure
    0.12
     zeroes
    0.11
     Want
    0.11
     isn
    0.11
    Activations Density 0.071%

    No Known Activations