© 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. 20972
    Prev
    Next
    INDEX
    Explanations

    island nation

    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
    æľŁåĨħ
    -0.10
    dt
    -0.10
    dit
    -0.10
    lew
    -0.09
    è¨ĢãģĪãģ°
    -0.09
    åİķ
    -0.09
    æªĶ
    -0.09
     CALLBACK
    -0.08
    avi
    -0.08
    empt
    -0.08
    POSITIVE LOGITS
    -wide
    0.10
    wide
    0.10
    mates
    0.09
    rock
    0.09
    numeric
    0.08
    åİŁæľīçļĦ
    0.08
    otify
    0.08
    èĩªæ²»
    0.08
    -même
    0.08
    worm
    0.08
    Activations Density 0.013%

    No Known Activations