© 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. 51746
    Prev
    Next
    INDEX
    Explanations

    raw

    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
    åħ¬è®¤çļĦ
    -0.10
    æIJ¦
    -0.10
    çĻ½å¤©
    -0.09
     Inhal
    -0.08
    ä»İ容
    -0.08
    /themes
    -0.08
    wig
    -0.08
     pry
    -0.08
     Inspir
    -0.07
    èİ«åIJį
    -0.07
    POSITIVE LOGITS
    /raw
    0.21
    raw
    0.20
     raw
    0.20
    (raw
    0.18
     Raw
    0.18
     rawData
    0.17
    .raw
    0.17
    	raw
    0.16
    Raw
    0.16
    åİŁå§ĭ
    0.16
    Activations Density 0.119%

    No Known Activations