© 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. 52146
    Prev
    Next
    INDEX
    Explanations

    news outlets

    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
    èĪ«
    -0.09
    atel
    -0.09
    ç¦Ģ
    -0.08
    æ´ĭ
    -0.08
    åĽ½æľī
    -0.08
    Ñī
    -0.08
    è¾ħ
    -0.08
    ount
    -0.08
    æĹłæķĮ
    -0.08
     Nin
    -0.08
    POSITIVE LOGITS
    aire
    0.11
    åħ¨çIJĥåĮĸ
    0.10
    æ´²
    0.10
    fern
    0.10
    chner
    0.09
    åĽ½éĻħåľ¨çº¿
    0.09
    ä¸Ńæĸĩ
    0.09
    ï¸
    0.09
    iÄį
    0.08
    åĿŀ
    0.08
    Activations Density 0.007%

    No Known Activations