© 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. 6948
    Prev
    Next
    INDEX
    Explanations

    pornography or cryptography

    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
    745
    -0.10
    gars
    -0.09
    woman
    -0.09
    call
    -0.08
    ooks
    -0.08
    Radians
    -0.08
     Edison
    -0.08
    uran
    -0.08
    cy
    -0.08
    erm
    -0.08
    POSITIVE LOGITS
    ographic
    0.10
     thicker
    0.10
     Camb
    0.10
    avr
    0.09
     camb
    0.09
    broker
    0.09
     [#
    0.09
    ographically
    0.09
     vl
    0.09
    .vertx
    0.08
    Activations Density 0.010%

    No Known Activations