© 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. 6752
    Prev
    Next
    INDEX
    Explanations

    dirty and clean states

    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
    intl
    -0.10
    -away
    -0.09
     stip
    -0.09
    ASE
    -0.09
    ening
    -0.09
    oning
    -0.09
    idf
    -0.08
     redeem
    -0.08
     Hass
    -0.08
    lee
    -0.08
    POSITIVE LOGITS
     Dirty
    0.12
     Ernst
    0.12
    ycz
    0.12
     hands
    0.10
    dirty
    0.10
     dirty
    0.10
    /Dk
    0.10
     ornaments
    0.10
    erna
    0.10
     ance
    0.10
    Activations Density 0.014%

    No Known Activations