© 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
    2. Qwen3-32B
    3. 32-RESID-BATCHTOPK-65K
    4. 21159
    Prev
    Next
    INDEX
    Explanations

    animal calls, specific terms

    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
    æĺ¯è¦ģ
    -0.09
    _ax
    -0.08
    SPACE
    -0.08
    çĶŁæ°Ķ
    -0.08
    kap
    -0.08
    ania
    -0.08
    gie
    -0.08
    æĺ¯åı¯ä»¥
    -0.08
    rides
    -0.08
    lass
    -0.08
    POSITIVE LOGITS
    ä½Ĺ
    0.10
    诱人
    0.09
    è¦ģçŁ¥éģĵ
    0.09
    æĮĸ
    0.09
    ĥģ
    0.08
    å®Ĺ
    0.08
    æĸĻ
    0.08
    æĨ¨
    0.08
    arg
    0.08
    tridge
    0.08
    Activations Density 0.005%

    No Known Activations