© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 18628
    Prev
    Next
    INDEX
    Explanations

    leaving nothing

    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
    Negative Logits
     intercourse
    -0.08
     penetr
    -0.08
    vp
    -0.08
     surve
    -0.08
    vr
    -0.08
     sex
    -0.08
     Sex
    -0.08
    vron
    -0.08
    Artifact
    -0.07
    ikel
    -0.07
    POSITIVE LOGITS
     nothing
    0.17
     none
    0.16
     nowhere
    0.16
     trails
    0.15
     no
    0.15
     NOTHING
    0.15
     nobody
    0.14
     neither
    0.14
     marks
    0.13
    nothing
    0.13
    Activations Density 0.007%

    No Known Activations