© 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. 28774
    Prev
    Next
    INDEX
    Explanations

    dick pic

    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
     herself
    -0.11
     pornstar
    -0.11
     himself
    -0.11
     belongs
    -0.10
     itself
    -0.10
     girlfriend
    -0.10
     woman
    -0.10
     Fever
    -0.10
     która
    -0.10
     his
    -0.10
    POSITIVE LOGITS
     themselves
    0.33
    their
    0.24
     their
    0.24
    Their
    0.23
     Their
    0.22
     yourselves
    0.20
     collectively
    0.20
     leurs
    0.19
    —they
    0.16
     THEIR
    0.15
    Activations Density 0.033%

    No Known Activations