© 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. 33001
    Prev
    Next
    INDEX
    Explanations

    removing unwanted things

    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
    rint
    -0.11
    eri
    -0.10
     relieved
    -0.10
     Releases
    -0.10
    ersed
    -0.10
    archical
    -0.09
     Hass
    -0.09
     Blob
    -0.09
    ensch
    -0.09
    sig
    -0.09
    POSITIVE LOGITS
     purge
    0.19
     cleanse
    0.18
     out
    0.17
     flushing
    0.15
     cleans
    0.15
     pur
    0.15
     unwanted
    0.14
     cleansing
    0.14
     expulsion
    0.13
     toxins
    0.13
    Activations Density 0.094%

    No Known Activations