© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 5802
    Prev
    Next
    INDEX
    Explanations

    cannot

    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
     unrestricted
    -0.11
    otti
    -0.09
    coli
    -0.08
     comer
    -0.08
     arbitrary
    -0.08
     Petty
    -0.08
    uyo
    -0.08
    acht
    -0.08
    arme
    -0.08
    омеÑĢ
    -0.08
    POSITIVE LOGITS
     cannot
    0.64
     unable
    0.61
     imposs
    0.56
     inability
    0.55
    cannot
    0.55
     Cannot
    0.55
     Unable
    0.53
    ä¸įèĥ½
    0.53
     incapable
    0.52
     impossible
    0.51
    Activations Density 2.458%

    No Known Activations