© 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. 116535
    Prev
    Next
    INDEX
    Explanations

    hiring a face painter

    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
     hang
    -0.11
     manic
    -0.10
     syn
    -0.10
    LV
    -0.09
    lite
    -0.09
     tur
    -0.09
     Kom
    -0.09
     accommodating
    -0.09
     Luk
    -0.09
    DEM
    -0.09
    POSITIVE LOGITS
     lug
    0.09
    ););↵
    0.08
    sep
    0.08
     wchar
    0.08
    opus
    0.08
    erval
    0.08
    TRUE
    0.08
    Routes
    0.08
     zd
    0.08
    adm
    0.08
    Activations Density 0.002%

    No Known Activations