© 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. 50339
    Prev
    Next
    INDEX
    Explanations

    http ://

    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
     gradually
    -0.09
     tit
    -0.09
    ingen
    -0.09
     Reyes
    -0.09
    CTS
    -0.09
    015
    -0.08
     stup
    -0.08
     unmarried
    -0.08
     Dial
    -0.08
     Dav
    -0.08
    POSITIVE LOGITS
     recip
    0.12
     ask
    0.11
     hands
    0.11
    éĹ®
    0.11
     EXPRESS
    0.10
     Hands
    0.10
     Ont
    0.10
     McGr
    0.10
     elusive
    0.10
     compare
    0.10
    Activations Density 0.002%

    No Known Activations