© 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. 29848
    Prev
    Next
    INDEX
    Explanations

    in response

    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
    quia
    -0.10
     Hank
    -0.10
     Bun
    -0.09
     compl
    -0.09
     unwilling
    -0.09
     immersed
    -0.08
    /by
    -0.08
     vor
    -0.08
     quien
    -0.08
     sequel
    -0.08
    POSITIVE LOGITS
    IRC
    0.10
    rnd
    0.09
     (!((
    0.09
    abad
    0.09
    elf
    0.09
    ono
    0.09
     gif
    0.09
    peng
    0.09
     homosex
    0.09
    imony
    0.09
    Activations Density 0.001%

    No Known Activations