© 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. 30325
    Prev
    Next
    INDEX
    Explanations

    everything all set

    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
     Sto
    -0.08
     Ending
    -0.08
    èŃ
    -0.08
     sto
    -0.08
     already
    -0.08
     tamp
    -0.08
     incl
    -0.07
     fulfil
    -0.07
     mash
    -0.07
     deepest
    -0.07
    POSITIVE LOGITS
     sorted
    0.18
     situated
    0.18
     organized
    0.15
     settled
    0.15
     arranged
    0.14
     squared
    0.14
    sorted
    0.14
     finished
    0.12
    organized
    0.12
     everything
    0.12
    Activations Density 0.079%

    No Known Activations