© 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. 8749
    Prev
    Next
    INDEX
    Explanations

    time since

    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
    è¿Ļä¸Ģ天
    -0.11
     PARTICULAR
    -0.10
    è¾ĪåŃIJ
    -0.09
    rego
    -0.09
    _sched
    -0.09
    éĻ¤æѤ
    -0.09
    _OW
    -0.08
    éĤķ
    -0.08
    åĩłåĪĨ
    -0.08
     Ñģиг
    -0.08
    POSITIVE LOGITS
    éªĸ
    0.09
    æľī人
    0.09
     Jam
    0.09
    éļıæŶéļıåľ°
    0.08
    å¾Ģ
    0.08
    èµı
    0.08
    ä¹°
    0.08
     zwyk
    0.08
    escaped
    0.08
    ward
    0.08
    Activations Density 0.014%

    No Known Activations