© 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. 21192
    Prev
    Next
    INDEX
    Explanations

    us house

    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
    _COLUMN
    -0.08
     Operator
    -0.08
    ocity
    -0.08
    æĮĤåľ¨
    -0.08
    æªĶ
    -0.08
    æ²¹èħ»
    -0.08
    æijĩ头
    -0.08
    iete
    -0.08
    ä½įåĪĹ
    -0.08
    _declaration
    -0.07
    POSITIVE LOGITS
    wares
    0.10
    çĽ¸ä¼ł
    0.08
    åŃIJéĩĮ
    0.08
    æĺİæĹ¥
    0.08
    ãĥ¼ãĤ¹
    0.08
    ouse
    0.08
    umen
    0.08
    åħīä¼ıåıijçĶµ
    0.08
    çĨĻ
    0.08
    æĺİçŁ¥
    0.08
    Activations Density 0.016%

    No Known Activations