© 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. 116989
    Prev
    Next
    INDEX
    Explanations

    I'm now here

    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
     however
    -0.14
     moreover
    -0.13
    however
    -0.12
     jedoch
    -0.11
     meanwhile
    -0.10
     sonst
    -0.10
    alo
    -0.10
     slightest
    -0.09
    Touches
    -0.09
     noticeably
    -0.09
    POSITIVE LOGITS
     basically
    0.12
     begs
    0.11
     Basically
    0.11
     naturally
    0.11
    Basically
    0.10
    oner
    0.10
     recap
    0.09
     essentially
    0.09
    ares
    0.09
     duly
    0.09
    Activations Density 0.263%

    No Known Activations