© 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. 7552
    Prev
    Next
    INDEX
    Explanations

    bottle or container lid

    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
    缩å°ı
    -0.12
    毯
    -0.10
    æĴķ
    -0.10
    缩
    -0.10
    èĻļ
    -0.09
    MinMax
    -0.09
    Ĥæķ°
    -0.09
    èĻļæĭŁ
    -0.09
    åħ±å»º
    -0.09
    åŁİå¸Ĥåıijå±ķ
    -0.09
    POSITIVE LOGITS
    yor
    0.09
    é©»
    0.08
    okus
    0.08
    æĥĨ
    0.08
    /pl
    0.08
     Homeland
    0.08
    çĥ¦æģ¼
    0.08
    dro
    0.08
    éĥ½å·²ç»ı
    0.08
    æĮģ
    0.08
    Activations Density 0.029%

    No Known Activations