© 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. 90426
    Prev
    Next
    INDEX
    Explanations

    wipe out

    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
     rop
    -0.10
     cors
    -0.10
    plist
    -0.09
     Succ
    -0.09
     sinking
    -0.09
     GRA
    -0.09
    .unregister
    -0.09
     bizarre
    -0.09
    brig
    -0.09
    dice
    -0.09
    POSITIVE LOGITS
     slate
    0.18
    wipe
    0.17
     clean
    0.15
     wiping
    0.15
     wipe
    0.15
     wiped
    0.14
     wipes
    0.13
     tears
    0.13
    -clean
    0.12
     Slate
    0.11
    Activations Density 0.014%

    No Known Activations