© 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. 35913
    Prev
    Next
    INDEX
    Explanations

    Sto, Stos, Stö

    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
    	TokenName
    -0.11
    è°ģçŁ¥
    -0.10
    oref
    -0.10
    bmp
    -0.10
    忱
    -0.09
    udes
    -0.09
     ordinal
    -0.09
     karÅŁÄ±s
    -0.09
    离åŃIJ
    -0.09
    æĺŁè¾°
    -0.09
    POSITIVE LOGITS
    holder
    0.11
    å³Ń
    0.10
    漫
    0.09
    esco
    0.09
    å¼Ĭ
    0.09
    ois
    0.08
    éĢłçº¸
    0.08
    åĵŃ
    0.08
    åı¸
    0.08
    haft
    0.08
    Activations Density 0.076%

    No Known Activations