© 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. 36674
    Prev
    Next
    INDEX
    Explanations

    pub/

    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
    boro
    -0.09
    sse
    -0.09
    fone
    -0.09
    å£ķ
    -0.08
    oire
    -0.08
    anton
    -0.08
     пом
    -0.08
    å£ģ
    -0.08
    interpreter
    -0.08
    BASH
    -0.08
    POSITIVE LOGITS
    (crate
    0.11
    eral
    0.10
    ience
    0.09
    æıļ
    0.09
    erate
    0.09
    (super
    0.08
    éĥ¨éķ¿
    0.08
    erator
    0.08
    ularity
    0.08
    ä¾µçĬ¯
    0.08
    Activations Density 0.052%

    No Known Activations