© 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. 9023
    Prev
    Next
    INDEX
    Explanations

    contrasting outcomes

    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
    ä½Ĩæĺ¯å¯¹äºİ
    -0.11
    ä½Ĩä»į
    -0.11
    ä¸įæİĴéĻ¤
    -0.11
    ä½łè¿ĺ
    -0.11
    ä¸į让
    -0.10
    è¿ĺå°Ĩ
    -0.10
    è¿ĺèĥ½
    -0.10
    å¦Ĥä½ķçľĭå¾ħ
    -0.10
    è¿Ļä¹Ī说
    -0.10
    å°ijä¸įäºĨ
    -0.10
    POSITIVE LOGITS
     Fou
    0.09
    ickle
    0.08
    sic
    0.08
    обÑĢа
    0.08
    Dest
    0.07
    oleon
    0.07
    ä¸ĵ项èµĦéĩij
    0.07
     gravity
    0.07
    angle
    0.07
    ogue
    0.07
    Activations Density 0.111%

    No Known Activations