© 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. 7065
    Prev
    Next
    INDEX
    Explanations

    manner of

    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
    otes
    -0.11
    omp
    -0.11
    iser
    -0.10
    YO
    -0.10
     beg
    -0.10
     ries
    -0.09
    oka
    -0.09
    prog
    -0.09
    _HS
    -0.09
    Persist
    -0.09
    POSITIVE LOGITS
    DRV
    0.10
     Wyn
    0.10
     readline
    0.08
     mat
    0.08
     impress
    0.08
    ³³³³³³³
    0.08
     NAN
    0.08
     Rab
    0.08
     prizes
    0.08
    cac
    0.08
    Activations Density 0.001%

    No Known Activations