© 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. 50111
    Prev
    Next
    INDEX
    Explanations

    stated goal

    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
     pathetic
    -0.10
     respons
    -0.09
    ovan
    -0.09
     damned
    -0.09
     humble
    -0.08
     invisible
    -0.08
     ['.
    -0.08
    uda
    -0.08
    angi
    -0.08
    SHARE
    -0.08
    POSITIVE LOGITS
     intend
    0.16
     protest
    0.15
     protesting
    0.15
     intent
    0.15
     intentions
    0.14
     intents
    0.14
     what
    0.13
     protested
    0.13
     intends
    0.13
     intention
    0.13
    Activations Density 0.034%

    No Known Activations