© 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. 116281
    Prev
    Next
    INDEX
    Explanations

    subgroup, function, lace, format, trial, approach, meme

    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
     crist
    -0.12
     helf
    -0.10
     hud
    -0.10
     ancestral
    -0.10
    ulle
    -0.10
     thereafter
    -0.10
     Geh
    -0.09
     hend
    -0.09
     christian
    -0.09
    JR
    -0.09
    POSITIVE LOGITS
     Mast
    0.09
    Orm
    0.09
     boyc
    0.08
     sneak
    0.08
    enen
    0.08
     unofficial
    0.08
    isi
    0.08
     hastily
    0.08
     Hast
    0.08
     Nim
    0.07
    Activations Density 0.296%

    No Known Activations