© 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. 7042
    Prev
    Next
    INDEX
    Explanations

    attempting to

    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
     handsome
    -0.08
     hare
    -0.08
     HT
    -0.08
     beautiful
    -0.07
     agreed
    -0.07
    sters
    -0.07
    fos
    -0.07
     SVN
    -0.07
    indi
    -0.07
     primal
    -0.07
    POSITIVE LOGITS
     unsuccessfully
    0.18
     attempts
    0.18
     tries
    0.17
     tried
    0.17
     Attempt
    0.16
     attempt
    0.16
    è¯ķ
    0.15
    attempt
    0.15
     attempted
    0.15
     Attempts
    0.15
    Activations Density 0.001%

    No Known Activations