© 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. 114836
    Prev
    Next
    INDEX
    Explanations

    whether to

    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
    uto
    -0.09
     bev
    -0.09
     upt
    -0.09
    agine
    -0.09
     serv
    -0.08
     Bew
    -0.08
     ther
    -0.08
     Gib
    -0.08
     Selected
    -0.08
     Myst
    -0.08
    POSITIVE LOGITS
    Should
    0.26
     Should
    0.25
    should
    0.22
     should
    0.22
    .Should
    0.20
    _should
    0.18
    .should
    0.16
     SHOULD
    0.16
     versus
    0.15
    æĺ¯åIJ¦
    0.14
    Activations Density 0.070%

    No Known Activations