© 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. 30251
    Prev
    Next
    INDEX
    Explanations

    start with activities

    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
     begin
    -0.12
     start
    -0.12
    å¼Ģå§ĭ
    -0.10
     beginning
    -0.10
     starters
    -0.10
     Starting
    -0.09
     begun
    -0.09
     Begin
    -0.09
     started
    -0.09
     began
    -0.09
    POSITIVE LOGITS
     sesión
    0.11
     inh
    0.11
     ect
    0.10
    обÑī
    0.10
    (Have
    0.10
     enlarg
    0.10
     Burr
    0.09
     encrypt
    0.09
    inbox
    0.09
     sex
    0.09
    Activations Density 0.045%

    No Known Activations