© 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. 113882
    Prev
    Next
    INDEX
    Explanations

    concerning asking you

    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
     Wing
    -0.10
     stamped
    -0.10
     SIMPLE
    -0.10
     Wein
    -0.10
     incon
    -0.10
     drowned
    -0.10
     Stern
    -0.09
     stom
    -0.09
    oz
    -0.09
     Ox
    -0.09
    POSITIVE LOGITS
     voluntarily
    0.12
     HQ
    0.11
     begging
    0.10
     skirt
    0.10
     defiance
    0.09
     defe
    0.09
     willingly
    0.09
     petition
    0.09
     offices
    0.09
    -approved
    0.09
    Activations Density 0.247%

    No Known Activations