© 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. 113980
    Prev
    Next
    INDEX
    Explanations

    fed up with

    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
     whip
    -0.10
    HEL
    -0.09
     Conc
    -0.08
     conc
    -0.08
    oli
    -0.08
     ASP
    -0.08
     imperson
    -0.07
    bos
    -0.07
     coc
    -0.07
     gd
    -0.07
    POSITIVE LOGITS
    JI
    0.11
     Harr
    0.10
    iful
    0.10
    izr
    0.10
     Bere
    0.10
     apologized
    0.10
     ness
    0.10
    extras
    0.10
     Correspond
    0.10
     Nichols
    0.10
    Activations Density 0.002%

    No Known Activations