© 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. 16735
    Prev
    Next
    INDEX
    Explanations

    man followed by certain suffixes or words

    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
    istes
    -0.10
    andre
    -0.09
    erton
    -0.09
    itet
    -0.09
    shan
    -0.09
    cco
    -0.09
    uras
    -0.08
    cv
    -0.08
    antom
    -0.08
    daq
    -0.08
    POSITIVE LOGITS
    hood
    0.28
    iac
    0.21
    hattan
    0.18
    agements
    0.18
    tras
    0.17
    agment
    0.17
    volent
    0.17
    liness
    0.16
    opause
    0.16
    made
    0.15
    Activations Density 0.178%

    No Known Activations