© 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. 113966
    Prev
    Next
    INDEX
    Explanations

    huge cocks and insertion

    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
     Glasses
    -0.13
     Opport
    -0.12
     opportun
    -0.12
     motel
    -0.12
     blackmail
    -0.12
     voyeur
    -0.12
     indeb
    -0.12
     opport
    -0.11
     naughty
    -0.11
     Dex
    -0.11
    POSITIVE LOGITS
     massive
    0.16
     huge
    0.13
     Massive
    0.12
     gigantic
    0.12
     extreme
    0.12
    huge
    0.11
     painful
    0.11
     insertion
    0.11
     Huge
    0.11
     enormous
    0.11
    Activations Density 0.017%

    No Known Activations