© 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. 115062
    Prev
    Next
    INDEX
    Explanations

    last part

    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
     Vo
    -0.11
     sou
    -0.10
    yen
    -0.10
    ayne
    -0.10
     gran
    -0.10
    vo
    -0.10
    /contact
    -0.10
     renamed
    -0.10
     Op
    -0.09
    Sou
    -0.09
    POSITIVE LOGITS
     part
    0.22
     mention
    0.21
     mentions
    0.18
     phrase
    0.17
     "...
    0.17
     last
    0.16
     mentioning
    0.16
     Mention
    0.16
     “âĢ¦
    0.15
     portion
    0.15
    Activations Density 0.318%

    No Known Activations