© 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. 87698
    Prev
    Next
    INDEX
    Explanations

    suck my, List the

    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
     hull
    -0.08
     Amnesty
    -0.08
     po
    -0.08
    hed
    -0.08
    ngr
    -0.08
    inel
    -0.08
     Nel
    -0.08
     breathing
    -0.08
     casa
    -0.08
     sliding
    -0.07
    POSITIVE LOGITS
     dirty
    0.11
    dirty
    0.11
    estar
    0.10
     Directed
    0.10
     Balls
    0.10
    ucc
    0.09
    LING
    0.09
    FK
    0.09
     balls
    0.09
    oden
    0.09
    Activations Density 0.002%

    No Known Activations