© 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. 112853
    Prev
    Next
    INDEX
    Explanations

    seeking advice or help

    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
    SHA
    -0.10
     Goals
    -0.10
    MF
    -0.09
    owe
    -0.09
     goals
    -0.09
    inker
    -0.09
     Till
    -0.09
     Supporting
    -0.08
     scl
    -0.08
     waiting
    -0.08
    POSITIVE LOGITS
     advice
    0.38
     Advice
    0.34
     guidance
    0.33
     assistance
    0.32
     help
    0.30
    Advice
    0.29
     Guidance
    0.27
     Assistance
    0.25
     advise
    0.21
     Help
    0.18
    Activations Density 0.357%

    No Known Activations