© 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. 14556
    Prev
    Next
    INDEX
    Explanations

    Despite advances, failure

    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
     hopefully
    -0.15
    bert
    -0.12
     surely
    -0.11
     Hopefully
    -0.11
     Masc
    -0.11
     luckily
    -0.11
    Hopefully
    -0.10
    ollo
    -0.10
    awah
    -0.10
     deserve
    -0.10
    POSITIVE LOGITS
     unfortunately
    0.20
     fails
    0.18
     suffers
    0.17
     sadly
    0.17
     alas
    0.16
     Unfortunately
    0.16
    Unfortunately
    0.16
     suffer
    0.14
     fail
    0.14
     cannot
    0.13
    Activations Density 0.945%

    No Known Activations