© 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. 6928
    Prev
    Next
    INDEX
    Explanations

    adverse consequences

    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
     situation
    -0.09
     reluct
    -0.08
     Schwe
    -0.08
    alen
    -0.07
     reason
    -0.07
     surroundings
    -0.07
     Bund
    -0.07
     perpetr
    -0.07
    letcher
    -0.06
    XS
    -0.06
    POSITIVE LOGITS
     confines
    0.24
     allure
    0.21
     comforts
    0.19
     lure
    0.19
     workings
    0.18
     wonders
    0.17
     joys
    0.17
     thrill
    0.17
     dictates
    0.17
     complexities
    0.17
    Activations Density 0.392%

    No Known Activations