© 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. 6527
    Prev
    Next
    INDEX
    Explanations

    after parked or times

    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
    ãģĦãģ¾ãģĻ
    -0.10
    ©ëĭĪëĭ¤
    -0.09
    ìŀħëĭĪëĭ¤
    -0.08
    ëĭĪëĭ¤
    -0.08
    íķ©ëĭĪëĭ¤
    -0.07
     TW
    -0.07
     ðŁĶ
    -0.07
    YO
    -0.07
     whipped
    -0.07
     fatally
    -0.06
    POSITIVE LOGITS
    æŶ
    0.36
    æĻĤ
    0.30
     times
    0.23
    åIJİ
    0.23
     when
    0.21
    ìľ¼ë©´
    0.20
    ë©´
    0.19
     afterwards
    0.18
    å¾Į
    0.17
     after
    0.17
    Activations Density 0.098%

    No Known Activations