© 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. 52017
    Prev
    Next
    INDEX
    Explanations

    later version or issues

    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
    aroo
    -0.11
    sWith
    -0.10
    ãĤĩ
    -0.10
    amel
    -0.09
    ä¾ĭå¤ĸ
    -0.09
    åIJİèĢħ
    -0.09
    ä¸ĭä¸Ģ代
    -0.09
    å¤ĸæĿ¥
    -0.09
     latter
    -0.09
    ä¸Ģ次
    -0.09
    POSITIVE LOGITS
    wards
    0.13
    -than
    0.12
    most
    0.12
    WARDS
    0.12
    Than
    0.11
    _than
    0.10
    Ñĩем
    0.10
    -stage
    0.10
    WARD
    0.10
    /new
    0.10
    Activations Density 0.040%

    No Known Activations