© 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. 15169
    Prev
    Next
    INDEX
    Explanations

    pure and clean

    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
    aroo
    -0.10
    hausen
    -0.09
     SQ
    -0.09
    ubi
    -0.09
    abit
    -0.09
     Wein
    -0.09
     Gul
    -0.08
    ovich
    -0.08
     prima
    -0.08
    Torrent
    -0.08
    POSITIVE LOGITS
     pure
    0.21
     purity
    0.20
    pure
    0.20
     Pure
    0.19
    bred
    0.19
    Pure
    0.17
    PURE
    0.16
     clean
    0.15
     Clean
    0.15
     cleanse
    0.14
    Activations Density 0.095%

    No Known Activations