© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 31220
    Prev
    Next
    INDEX
    Explanations

    reference markers

    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
     wh
    -0.11
    ROP
    -0.09
     insured
    -0.09
     cont
    -0.09
     lit
    -0.09
     Sit
    -0.08
     bloody
    -0.08
     veh
    -0.08
     diag
    -0.08
     optionally
    -0.08
    POSITIVE LOGITS
     -:
    0.10
    iov
    0.09
    addContainerGap
    0.09
    Ping
    0.08
    chk
    0.08
    aken
    0.08
    ãĥĥãĥĪ
    0.08
    .mk
    0.08
    flip
    0.08
    gnore
    0.08
    Activations Density 0.175%

    No Known Activations