© 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. 48131
    Prev
    Next
    INDEX
    Explanations

    I describing issues

    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
    /ref
    -0.10
     forb
    -0.09
     Antarctic
    -0.09
     Convenient
    -0.08
     conveniently
    -0.08
    croft
    -0.08
     harassing
    -0.08
     ringing
    -0.08
    ={}
    -0.08
     convenient
    -0.08
    POSITIVE LOGITS
     checked
    0.12
     inconsist
    0.12
    Checked
    0.12
     Checked
    0.12
     ruled
    0.11
    brand
    0.11
     Tried
    0.11
     ruling
    0.11
     tested
    0.11
     identical
    0.11
    Activations Density 0.966%

    No Known Activations