© 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. 52196
    Prev
    Next
    INDEX
    Explanations

    problems or difficulties

    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
    éĥ½æĥ³
    -0.10
    åıĺ为
    -0.09
    ä¸Ģç¬Ķ
    -0.09
    æĥ³è¿ĩ
    -0.08
    æ²®
    -0.08
    è°¤
    -0.08
    èµ·æĿ¥äºĨ
    -0.08
     ÑħоÑĤ
    -0.08
    ä¹İ
    -0.08
    æ¸Ĭ
    -0.08
    POSITIVE LOGITS
    ueue
    0.10
    IDES
    0.09
     Stir
    0.08
    UpDown
    0.08
     Patt
    0.08
     اÙĦتش
    0.08
    .MEDIA
    0.08
     اÙĦÙĤض
    0.08
    è§ī
    0.08
    èĬĴ
    0.08
    Activations Density 0.010%

    No Known Activations