© 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. 18884
    Prev
    Next
    INDEX
    Explanations

    copyright notice

    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
    åĪ»
    -0.10
    å²Ķ
    -0.09
    ä¹ĭæĺŁ
    -0.09
    ç®Ĺ
    -0.09
    bane
    -0.09
    dess
    -0.09
    åĵĪå°Ķ
    -0.09
    åŃ¦å®¶
    -0.09
    çļĦæł¹æľ¬
    -0.09
    æłĩè®°
    -0.09
    POSITIVE LOGITS
    rut
    0.09
     McGu
    0.09
    解æĶ¾
    0.09
    转åıij
    0.09
     Tob
    0.08
    çľĭäºĨä¸Ģçľ¼
    0.08
     Abs
    0.08
    abs
    0.08
    beer
    0.08
    cheid
    0.08
    Activations Density 0.052%

    No Known Activations