© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 9499
    Prev
    Next
    INDEX
    Explanations

    driving home

    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
    æĿĤ
    -0.09
    çĤ¬
    -0.09
    _flight
    -0.09
    妩
    -0.08
    æķ´çIJĨ
    -0.08
    ä¸įçŁ¥
    -0.08
    åĺı
    -0.08
    rowable
    -0.08
    èĭĴ
    -0.08
    çķı
    -0.08
    POSITIVE LOGITS
    illet
    0.10
    iles
    0.09
    iki
    0.09
    溽
    0.09
    gend
    0.09
     brink
    0.08
    à¸ģะ
    0.08
    åį¯
    0.08
    åİĭå®ŀ
    0.08
    çīºçī²
    0.08
    Activations Density 0.048%

    No Known Activations