© 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. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 21954
    Prev
    Next
    INDEX
    Explanations

    determined to be

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    adamkarvonen/qwen3-32b-saes/saes_Qwen_Qwen3-32B_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
    оÑĢо
    -0.09
    ç´§æĢ¥
    -0.09
     ÑħÑĢ
    -0.08
    æģIJæħĮ
    -0.08
    ablo
    -0.08
    rä
    -0.08
    ðŁijĩ
    -0.08
    able
    -0.08
    rap
    -0.08
    rawl
    -0.08
    POSITIVE LOGITS
    åĭĥåĭĥ
    0.15
    íŀĪ
    0.11
    ente
    0.10
    енно
    0.10
    æ¯ħåĬĽ
    0.10
    ly
    0.09
    leÅŁ
    0.09
    æĹĥ
    0.09
    æĬĹæĹ¥
    0.09
    åıµ
    0.09
    Activations Density 0.010%

    No Known Activations