© 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. 111925
    Prev
    Next
    INDEX
    Explanations

    letter following date/June

    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
    orra
    -0.10
     balk
    -0.10
    Backdrop
    -0.09
     interviewer
    -0.09
    æĴŃ
    -0.09
     Podcast
    -0.09
     mantra
    -0.09
     Mic
    -0.09
     mic
    -0.09
     Kylie
    -0.08
    POSITIVE LOGITS
     letter
    0.52
     Letter
    0.46
     letters
    0.44
    letter
    0.41
    Letter
    0.40
     Letters
    0.39
     LETTER
    0.38
    -letter
    0.36
    _letter
    0.34
    letters
    0.33
    Activations Density 0.269%

    No Known Activations