© 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. 48017
    Prev
    Next
    INDEX
    Explanations

    contaminant or damage residue

    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
     Welch
    -0.11
    neau
    -0.10
     Reve
    -0.10
     Grip
    -0.10
    .Init
    -0.09
    halt
    -0.09
     Pond
    -0.09
     urgency
    -0.09
    borg
    -0.09
     native
    -0.09
    POSITIVE LOGITS
     indirect
    0.26
     indirectly
    0.26
     residual
    0.26
     stray
    0.23
     spill
    0.22
     spilled
    0.22
     overflow
    0.21
     proximity
    0.21
     fallout
    0.21
     leftover
    0.20
    Activations Density 0.407%

    No Known Activations