© 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. 48056
    Prev
    Next
    INDEX
    Explanations

    will check better

    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
     Nikol
    -0.10
     Dane
    -0.10
     ime
    -0.10
     snap
    -0.09
    ide
    -0.09
    IKE
    -0.09
    ante
    -0.09
    .native
    -0.09
    ierz
    -0.09
    uche
    -0.09
    POSITIVE LOGITS
     ill
    0.16
     Ill
    0.16
    'll
    0.14
    ç¨į
    0.14
    ’ll
    0.13
     await
    0.13
     will
    0.12
    will
    0.12
     we
    0.12
     meet
    0.12
    Activations Density 0.081%

    No Known Activations