© 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. 46388
    Prev
    Next
    INDEX
    Explanations

    disable, repeal, derail

    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
     unnecessary
    -0.09
     practically
    -0.09
     Hass
    -0.09
    previous
    -0.08
    uso
    -0.08
     nearly
    -0.08
     Whit
    -0.07
     virtually
    -0.07
    kb
    -0.07
    oted
    -0.07
    POSITIVE LOGITS
     newfound
    0.15
     altogether
    0.13
     prematurely
    0.12
     fatally
    0.12
    pell
    0.11
    olla
    0.11
    osp
    0.11
     careful
    0.11
     Alto
    0.10
    /delete
    0.10
    Activations Density 0.126%

    No Known Activations