© 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. 17454
    Prev
    Next
    INDEX
    Explanations

    cum + suffix

    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
    ette
    -0.08
    eer
    -0.08
     batch
    -0.07
     dumb
    -0.07
    ides
    -0.07
    isch
    -0.07
    rez
    -0.07
    unde
    -0.07
    ized
    -0.07
    IRON
    -0.06
    POSITIVE LOGITS
    ming
    0.18
    bersome
    0.16
    ulative
    0.16
    mins
    0.16
    MING
    0.15
    ing
    0.15
     stains
    0.13
    iskey
    0.13
     stain
    0.13
    mul
    0.13
    Activations Density 0.004%

    No Known Activations