© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 47552
    Prev
    Next
    INDEX
    Explanations

    reporting speech or attribution

    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
    aler
    -0.12
    mens
    -0.11
    inters
    -0.11
     DER
    -0.10
     marsh
    -0.10
    shiv
    -0.10
    ãĥķ
    -0.09
     tidy
    -0.09
    718
    -0.09
     discontin
    -0.09
    POSITIVE LOGITS
    acia
    0.09
     aprove
    0.09
     attachments
    0.09
     fidelity
    0.09
     qual
    0.08
     attachment
    0.08
     Gregg
    0.08
     McKin
    0.08
     Jude
    0.08
     therein
    0.08
    Activations Density 0.013%

    No Known Activations