© 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. 26148
    Prev
    Next
    INDEX
    Explanations

    Dick names, especially surnames

    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
    gable
    -0.09
    latable
    -0.08
     intellectually
    -0.08
    atable
    -0.08
     hans
    -0.08
     requis
    -0.08
    enko
    -0.08
    able
    -0.07
     beige
    -0.07
     nons
    -0.07
    POSITIVE LOGITS
    inson
    0.17
    blick
    0.13
    enson
    0.13
     Cheney
    0.12
    ety
    0.11
    sher
    0.11
    ory
    0.11
    erson
    0.10
    heads
    0.10
    fore
    0.10
    Activations Density 0.007%

    No Known Activations