© 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. 48621
    Prev
    Next
    INDEX
    Explanations

    So, a clause begins

    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
    proved
    -0.09
    oment
    -0.09
    ,
    -0.08
     ung
    -0.08
     beh
    -0.08
    acam
    -0.08
    âĢ¦but
    -0.08
    ADB
    -0.08
    Liked
    -0.08
    PTY
    -0.08
    POSITIVE LOGITS
    aring
    0.14
     naturally
    0.13
     mote
    0.12
    ftware
    0.11
    -called
    0.11
     bottoms
    0.10
    oner
    0.10
    reas
    0.10
    ber
    0.10
    ink
    0.09
    Activations Density 0.017%

    No Known Activations