© 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. 16182
    Prev
    Next
    INDEX
    Explanations

    ðŁ emoji characters

    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
    ÃĤ
    -0.16
    .htm
    -0.13
    Ãĥ
    -0.13
    ?a
    -0.12
     ÃĤ
    -0.12
    /////////////////////////////////////////////////////////////////////////////↵
    -0.12
    \\\\
    -0.12
    ġ
    -0.12
    ~
    -0.11
    \\
    -0.11
    POSITIVE LOGITS
     ðŁ
    0.26
     ðŁĴ
    0.25
     ðŁij
    0.24
    ðŁĴ
    0.23
     ðŁĶ
    0.23
    ðŁ
    0.21
     ðŁĺ
    0.19
    ï¸ı
    0.19
     emoji
    0.16
     á
    0.16
    Activations Density 0.102%

    No Known Activations