© 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. 87682
    Prev
    Next
    INDEX
    Explanations

    freaking out, fucking up, absolute

    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
    ie
    -0.11
     mere
    -0.10
    iam
    -0.10
    mere
    -0.09
    oshi
    -0.09
    ahlen
    -0.09
    itty
    -0.09
    sez
    -0.09
     upcoming
    -0.09
     utter
    -0.09
    POSITIVE LOGITS
    /false
    0.11
     terrified
    0.10
     hilarious
    0.09
     tailor
    0.09
    hra
    0.09
     prive
    0.08
    aneously
    0.08
    haust
    0.08
     Wir
    0.08
    hm
    0.08
    Activations Density 0.003%

    No Known Activations