© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 31299
    Prev
    Next
    INDEX
    Explanations

    automotive infotainment systems and devices

    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
    olina
    -0.09
    åħ¨éķ¿
    -0.09
     Examiner
    -0.08
    æī¿è½½
    -0.08
    æķĻèĤ²æķĻåѦ
    -0.08
    UPS
    -0.08
    æ½ľåĬĽ
    -0.08
    :event
    -0.08
    ç©¿ä¸Ĭ
    -0.08
    åıĺè¿ģ
    -0.08
    POSITIVE LOGITS
     MMI
    0.10
    èĩªé©¾
    0.09
    åľ¨è·¯ä¸Ĭ
    0.09
    车åĨħ
    0.09
    æĢł
    0.08
    маг
    0.08
    车载
    0.08
     inset
    0.08
    æį©
    0.08
    ç³»
    0.08
    Activations Density 0.154%

    No Known Activations