© 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. 5271
    Prev
    Next
    INDEX
    Explanations

    Hybrid

    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
     Cliff
    -0.10
     dildo
    -0.10
     Tow
    -0.10
     kel
    -0.09
    zn
    -0.09
    oward
    -0.09
     Kel
    -0.08
     cust
    -0.08
     judged
    -0.08
     Probably
    -0.08
    POSITIVE LOGITS
     Witness
    0.13
     Discover
    0.11
    Discover
    0.11
    Witness
    0.11
     Hey
    0.11
    Hey
    0.11
     Asi
    0.11
    Experience
    0.11
    Forget
    0.10
     ðŁĶ
    0.10
    Activations Density 0.021%

    No Known Activations