© 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. 20920
    Prev
    Next
    INDEX
    Explanations

    parallel vector, parallel group, parallel lines, parallel Ajax

    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
    ãģŁãĤģãģ«
    -0.09
    elyn
    -0.08
    çĶ©
    -0.08
    èĭĮ
    -0.08
    yla
    -0.08
    _fake
    -0.08
    éķ¿è¿ľ
    -0.08
    _verified
    -0.08
    ân
    -0.08
    utt
    -0.08
    POSITIVE LOGITS
    mente
    0.12
     minded
    0.12
    ism
    0.12
    -minded
    0.11
    æĪĸå¤ļ
    0.11
    éªĽ
    0.11
    izable
    0.10
    æĿł
    0.09
    .parallel
    0.09
     parallel
    0.09
    Activations Density 0.030%

    No Known Activations