© 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. 113202
    Prev
    Next
    INDEX
    Explanations

    conceptually or logically measuring

    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
     folks
    -0.12
     fancy
    -0.11
     tricky
    -0.11
     nutshell
    -0.10
     tough
    -0.10
     goodies
    -0.10
     cozy
    -0.10
     comfy
    -0.10
     cosy
    -0.10
     chic
    -0.10
    POSITIVE LOGITS
     statistically
    0.16
     optimum
    0.16
     il
    0.16
     inefficient
    0.15
     Probability
    0.15
     logically
    0.15
     approximately
    0.15
     logical
    0.15
     extrapol
    0.14
     probability
    0.14
    Activations Density 0.110%

    No Known Activations