© 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. 116524
    Prev
    Next
    INDEX
    Explanations

    provided under

    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
     Nos
    -0.12
    apel
    -0.12
    pio
    -0.12
    ucha
    -0.11
    Nos
    -0.11
    bose
    -0.11
    asso
    -0.11
     ÑĩÑĤобÑĭ
    -0.11
     Shack
    -0.11
    iej
    -0.11
    POSITIVE LOGITS
    unde
    0.07
     dod
    0.07
     dare
    0.06
     examiner
    0.06
     differentiate
    0.06
     Examiner
    0.06
     Crime
    0.06
     chron
    0.06
     lining
    0.06
     revolution
    0.06
    Activations Density 0.001%

    No Known Activations