© 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. 113544
    Prev
    Next
    INDEX
    Explanations

    no matter what I try

    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
    ç³»
    -0.11
     arguably
    -0.11
    ernes
    -0.11
    lla
    -0.10
    966
    -0.10
     Sym
    -0.10
    ipes
    -0.10
    logan
    -0.10
     Banner
    -0.10
     Cove
    -0.10
    POSITIVE LOGITS
     cannot
    0.19
     couldn
    0.17
     Cannot
    0.16
     unable
    0.15
    cannot
    0.15
    Unable
    0.14
     Unable
    0.13
     cant
    0.13
    Cannot
    0.13
    ä¸įèĥ½
    0.13
    Activations Density 0.037%

    No Known Activations