© 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. 29800
    Prev
    Next
    INDEX
    Explanations

    fuck

    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
     Twin
    -0.11
     impro
    -0.10
    keh
    -0.10
    edith
    -0.09
    HU
    -0.09
     silly
    -0.09
    cpt
    -0.09
     convincing
    -0.09
     singleton
    -0.09
     Isn
    -0.09
    POSITIVE LOGITS
     fucking
    0.21
     FUCK
    0.16
     dare
    0.16
     Fucking
    0.14
     fuck
    0.14
     Fuck
    0.13
    Fuck
    0.13
     touch
    0.12
    fuck
    0.11
     touches
    0.10
    Activations Density 0.123%

    No Known Activations