© 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. 54784
    Prev
    Next
    INDEX
    Explanations

    priority areas

    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®ŀè·µç»ıéªĮ
    -0.10
    æĿ¥è¯´
    -0.09
    çħ§
    -0.09
    缸åħ³äººåijĺ
    -0.09
    .Bounds
    -0.09
    _bm
    -0.08
    åıĮèµ¢
    -0.08
    oser
    -0.08
    èµ·åĪ°
    -0.08
    obi
    -0.08
    POSITIVE LOGITS
    åħ³åĪĩ
    0.14
    éĩįçĤ¹
    0.13
    çĿĢéĩį
    0.13
    éĩįçĤ¹åħ³æ³¨
    0.12
    ä¸ī大
    0.11
    éĩįé»ŀ
    0.11
    çªģåĩº
    0.11
    åħ³æ³¨
    0.11
     focus
    0.11
    çļĦéĩįçĤ¹
    0.10
    Activations Density 0.086%

    No Known Activations