© 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. 30198
    Prev
    Next
    INDEX
    Explanations

    pornography

    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
     laps
    -0.10
     CGI
    -0.10
     cgi
    -0.10
    beb
    -0.10
     GG
    -0.09
     GI
    -0.09
     conceded
    -0.09
    ibi
    -0.09
     sn
    -0.09
    é¦
    -0.09
    POSITIVE LOGITS
     Screw
    0.13
     screw
    0.12
     cancell
    0.10
    erek
    0.09
     Rupert
    0.09
    fv
    0.09
    locker
    0.09
    .Lock
    0.09
     Kak
    0.09
    upert
    0.09
    Activations Density 0.034%

    No Known Activations