© 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. 5882
    Prev
    Next
    INDEX
    Explanations

    intermediate between

    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
    gart
    -0.12
    arus
    -0.10
     paired
    -0.10
     Blackburn
    -0.10
    adh
    -0.10
    vens
    -0.09
    otal
    -0.09
     association
    -0.09
     Lebens
    -0.09
     Budd
    -0.08
    POSITIVE LOGITS
     intermediate
    0.48
     midway
    0.44
     intermediary
    0.41
     Intermediate
    0.40
     halfway
    0.40
     middle
    0.36
    Intermediate
    0.35
     somewhere
    0.34
     intermedi
    0.33
     between
    0.30
    Activations Density 0.475%

    No Known Activations