© 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. 28289
    Prev
    Next
    INDEX
    Explanations

    expresses being wrong

    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
     delicate
    -0.08
    rans
    -0.08
     Dip
    -0.08
     debris
    -0.08
    nu
    -0.08
    ÃŃn
    -0.07
     Lo
    -0.07
    ugal
    -0.07
    ugh
    -0.07
    609
    -0.07
    POSITIVE LOGITS
     asses
    0.11
    /init
    0.11
     Extras
    0.11
     Independ
    0.11
    bare
    0.11
    OI
    0.11
    aters
    0.10
    ikon
    0.10
     compl
    0.10
     Pause
    0.10
    Activations Density 0.005%

    No Known Activations