© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 7067
    Prev
    Next
    INDEX
    Explanations

    Mali, ites, elian, -cell

    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
    ize
    -0.11
    èݽ
    -0.10
    çĦ¶æĺ¯
    -0.10
    ÑĤал
    -0.10
    大家åĪĨ享
    -0.09
    ÑģÑĤи
    -0.09
     bil
    -0.09
    AMI
    -0.09
    idel
    -0.08
    sWith
    -0.08
    POSITIVE LOGITS
    åĩºè¡Ģ
    0.09
    ited
    0.09
    å·§
    0.08
    _BUFF
    0.08
    ittest
    0.08
    icl
    0.08
    ander
    0.08
    unist
    0.08
    举
    0.08
    iteration
    0.08
    Activations Density 0.005%

    No Known Activations