© 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. 31931
    Prev
    Next
    INDEX
    Explanations

    That said, that being said, having said that

    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
    amma
    -0.11
    lik
    -0.10
     Factory
    -0.10
    igos
    -0.10
    avel
    -0.10
     lire
    -0.10
    ê·¸
    -0.09
    -fit
    -0.09
    asp
    -0.09
     Jeg
    -0.09
    POSITIVE LOGITS
    rans
    0.10
     pam
    0.09
     reservations
    0.09
     duly
    0.08
     Arch
    0.08
    eve
    0.08
     indul
    0.08
     despre
    0.08
    urs
    0.08
     Stern
    0.08
    Activations Density 0.009%

    No Known Activations