© 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. 53099
    Prev
    Next
    INDEX
    Explanations

    first glance / seems / appears

    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
    å§Ĭ
    -0.10
    asting
    -0.09
    _mA
    -0.09
    æŀģå°ij
    -0.09
    .Zoom
    -0.09
     Tec
    -0.09
    ä¿¡çĶ¨
    -0.09
    驯
    -0.09
    åħ¶å®ĥéĹ®é¢ĺ
    -0.08
    çŀİ
    -0.08
    POSITIVE LOGITS
    çľĭèµ·æĿ¥
    0.25
    çľĭèµ·ä¾Ĩ
    0.22
    çľĭä¸Ĭåİ»
    0.22
    åIJ¬èµ·æĿ¥
    0.21
    æĺ¾å¾Ĺ
    0.20
    çľĭæĿ¥
    0.19
    ä¼¼ä¹İ
    0.18
     seems
    0.17
     seem
    0.17
    好åĥıæĺ¯
    0.17
    Activations Density 0.108%

    No Known Activations